goal case study method

• Privacy Policy

Home » Case Study – Methods, Examples and Guide

Case Study – Methods, Examples and Guide

Table of Contents

A case study is a research method that involves an in-depth examination and analysis of a particular phenomenon or case, such as an individual, organization, community, event, or situation.

It is a qualitative research approach that aims to provide a detailed and comprehensive understanding of the case being studied. Case studies typically involve multiple sources of data, including interviews, observations, documents, and artifacts, which are analyzed using various techniques, such as content analysis, thematic analysis, and grounded theory. The findings of a case study are often used to develop theories, inform policy or practice, or generate new research questions.

Types of Case Study

Types and Methods of Case Study are as follows:

Single-Case Study

A single-case study is an in-depth analysis of a single case. This type of case study is useful when the researcher wants to understand a specific phenomenon in detail.

For Example , A researcher might conduct a single-case study on a particular individual to understand their experiences with a particular health condition or a specific organization to explore their management practices. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as content analysis or thematic analysis. The findings of a single-case study are often used to generate new research questions, develop theories, or inform policy or practice.

Multiple-Case Study

A multiple-case study involves the analysis of several cases that are similar in nature. This type of case study is useful when the researcher wants to identify similarities and differences between the cases.

For Example, a researcher might conduct a multiple-case study on several companies to explore the factors that contribute to their success or failure. The researcher collects data from each case, compares and contrasts the findings, and uses various techniques to analyze the data, such as comparative analysis or pattern-matching. The findings of a multiple-case study can be used to develop theories, inform policy or practice, or generate new research questions.

Exploratory Case Study

An exploratory case study is used to explore a new or understudied phenomenon. This type of case study is useful when the researcher wants to generate hypotheses or theories about the phenomenon.

For Example, a researcher might conduct an exploratory case study on a new technology to understand its potential impact on society. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as grounded theory or content analysis. The findings of an exploratory case study can be used to generate new research questions, develop theories, or inform policy or practice.

Descriptive Case Study

A descriptive case study is used to describe a particular phenomenon in detail. This type of case study is useful when the researcher wants to provide a comprehensive account of the phenomenon.

For Example, a researcher might conduct a descriptive case study on a particular community to understand its social and economic characteristics. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as content analysis or thematic analysis. The findings of a descriptive case study can be used to inform policy or practice or generate new research questions.

Instrumental Case Study

An instrumental case study is used to understand a particular phenomenon that is instrumental in achieving a particular goal. This type of case study is useful when the researcher wants to understand the role of the phenomenon in achieving the goal.

For Example, a researcher might conduct an instrumental case study on a particular policy to understand its impact on achieving a particular goal, such as reducing poverty. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as content analysis or thematic analysis. The findings of an instrumental case study can be used to inform policy or practice or generate new research questions.

Case Study Data Collection Methods

Here are some common data collection methods for case studies:

Interviews involve asking questions to individuals who have knowledge or experience relevant to the case study. Interviews can be structured (where the same questions are asked to all participants) or unstructured (where the interviewer follows up on the responses with further questions). Interviews can be conducted in person, over the phone, or through video conferencing.

Observations

Observations involve watching and recording the behavior and activities of individuals or groups relevant to the case study. Observations can be participant (where the researcher actively participates in the activities) or non-participant (where the researcher observes from a distance). Observations can be recorded using notes, audio or video recordings, or photographs.

Documents can be used as a source of information for case studies. Documents can include reports, memos, emails, letters, and other written materials related to the case study. Documents can be collected from the case study participants or from public sources.

Surveys involve asking a set of questions to a sample of individuals relevant to the case study. Surveys can be administered in person, over the phone, through mail or email, or online. Surveys can be used to gather information on attitudes, opinions, or behaviors related to the case study.

Artifacts are physical objects relevant to the case study. Artifacts can include tools, equipment, products, or other objects that provide insights into the case study phenomenon.

How to conduct Case Study Research

Conducting a case study research involves several steps that need to be followed to ensure the quality and rigor of the study. Here are the steps to conduct case study research:

• Define the research questions: The first step in conducting a case study research is to define the research questions. The research questions should be specific, measurable, and relevant to the case study phenomenon under investigation.
• Select the case: The next step is to select the case or cases to be studied. The case should be relevant to the research questions and should provide rich and diverse data that can be used to answer the research questions.
• Collect data: Data can be collected using various methods, such as interviews, observations, documents, surveys, and artifacts. The data collection method should be selected based on the research questions and the nature of the case study phenomenon.
• Analyze the data: The data collected from the case study should be analyzed using various techniques, such as content analysis, thematic analysis, or grounded theory. The analysis should be guided by the research questions and should aim to provide insights and conclusions relevant to the research questions.
• Draw conclusions: The conclusions drawn from the case study should be based on the data analysis and should be relevant to the research questions. The conclusions should be supported by evidence and should be clearly stated.
• Validate the findings: The findings of the case study should be validated by reviewing the data and the analysis with participants or other experts in the field. This helps to ensure the validity and reliability of the findings.
• Write the report: The final step is to write the report of the case study research. The report should provide a clear description of the case study phenomenon, the research questions, the data collection methods, the data analysis, the findings, and the conclusions. The report should be written in a clear and concise manner and should follow the guidelines for academic writing.

Examples of Case Study

Here are some examples of case study research:

• The Hawthorne Studies : Conducted between 1924 and 1932, the Hawthorne Studies were a series of case studies conducted by Elton Mayo and his colleagues to examine the impact of work environment on employee productivity. The studies were conducted at the Hawthorne Works plant of the Western Electric Company in Chicago and included interviews, observations, and experiments.
• The Stanford Prison Experiment: Conducted in 1971, the Stanford Prison Experiment was a case study conducted by Philip Zimbardo to examine the psychological effects of power and authority. The study involved simulating a prison environment and assigning participants to the role of guards or prisoners. The study was controversial due to the ethical issues it raised.
• The Challenger Disaster: The Challenger Disaster was a case study conducted to examine the causes of the Space Shuttle Challenger explosion in 1986. The study included interviews, observations, and analysis of data to identify the technical, organizational, and cultural factors that contributed to the disaster.
• The Enron Scandal: The Enron Scandal was a case study conducted to examine the causes of the Enron Corporation’s bankruptcy in 2001. The study included interviews, analysis of financial data, and review of documents to identify the accounting practices, corporate culture, and ethical issues that led to the company’s downfall.
• The Fukushima Nuclear Disaster : The Fukushima Nuclear Disaster was a case study conducted to examine the causes of the nuclear accident that occurred at the Fukushima Daiichi Nuclear Power Plant in Japan in 2011. The study included interviews, analysis of data, and review of documents to identify the technical, organizational, and cultural factors that contributed to the disaster.

Application of Case Study

Case studies have a wide range of applications across various fields and industries. Here are some examples:

Business and Management

Case studies are widely used in business and management to examine real-life situations and develop problem-solving skills. Case studies can help students and professionals to develop a deep understanding of business concepts, theories, and best practices.

Case studies are used in healthcare to examine patient care, treatment options, and outcomes. Case studies can help healthcare professionals to develop critical thinking skills, diagnose complex medical conditions, and develop effective treatment plans.

Case studies are used in education to examine teaching and learning practices. Case studies can help educators to develop effective teaching strategies, evaluate student progress, and identify areas for improvement.

Social Sciences

Case studies are widely used in social sciences to examine human behavior, social phenomena, and cultural practices. Case studies can help researchers to develop theories, test hypotheses, and gain insights into complex social issues.

Law and Ethics

Case studies are used in law and ethics to examine legal and ethical dilemmas. Case studies can help lawyers, policymakers, and ethical professionals to develop critical thinking skills, analyze complex cases, and make informed decisions.

Purpose of Case Study

The purpose of a case study is to provide a detailed analysis of a specific phenomenon, issue, or problem in its real-life context. A case study is a qualitative research method that involves the in-depth exploration and analysis of a particular case, which can be an individual, group, organization, event, or community.

The primary purpose of a case study is to generate a comprehensive and nuanced understanding of the case, including its history, context, and dynamics. Case studies can help researchers to identify and examine the underlying factors, processes, and mechanisms that contribute to the case and its outcomes. This can help to develop a more accurate and detailed understanding of the case, which can inform future research, practice, or policy.

Case studies can also serve other purposes, including:

• Illustrating a theory or concept: Case studies can be used to illustrate and explain theoretical concepts and frameworks, providing concrete examples of how they can be applied in real-life situations.
• Developing hypotheses: Case studies can help to generate hypotheses about the causal relationships between different factors and outcomes, which can be tested through further research.
• Providing insight into complex issues: Case studies can provide insights into complex and multifaceted issues, which may be difficult to understand through other research methods.
• Informing practice or policy: Case studies can be used to inform practice or policy by identifying best practices, lessons learned, or areas for improvement.

Advantages of Case Study Research

There are several advantages of case study research, including:

• In-depth exploration: Case study research allows for a detailed exploration and analysis of a specific phenomenon, issue, or problem in its real-life context. This can provide a comprehensive understanding of the case and its dynamics, which may not be possible through other research methods.
• Rich data: Case study research can generate rich and detailed data, including qualitative data such as interviews, observations, and documents. This can provide a nuanced understanding of the case and its complexity.
• Holistic perspective: Case study research allows for a holistic perspective of the case, taking into account the various factors, processes, and mechanisms that contribute to the case and its outcomes. This can help to develop a more accurate and comprehensive understanding of the case.
• Theory development: Case study research can help to develop and refine theories and concepts by providing empirical evidence and concrete examples of how they can be applied in real-life situations.
• Practical application: Case study research can inform practice or policy by identifying best practices, lessons learned, or areas for improvement.
• Contextualization: Case study research takes into account the specific context in which the case is situated, which can help to understand how the case is influenced by the social, cultural, and historical factors of its environment.

Limitations of Case Study Research

There are several limitations of case study research, including:

• Limited generalizability : Case studies are typically focused on a single case or a small number of cases, which limits the generalizability of the findings. The unique characteristics of the case may not be applicable to other contexts or populations, which may limit the external validity of the research.
• Biased sampling: Case studies may rely on purposive or convenience sampling, which can introduce bias into the sample selection process. This may limit the representativeness of the sample and the generalizability of the findings.
• Subjectivity: Case studies rely on the interpretation of the researcher, which can introduce subjectivity into the analysis. The researcher’s own biases, assumptions, and perspectives may influence the findings, which may limit the objectivity of the research.
• Limited control: Case studies are typically conducted in naturalistic settings, which limits the control that the researcher has over the environment and the variables being studied. This may limit the ability to establish causal relationships between variables.
• Time-consuming: Case studies can be time-consuming to conduct, as they typically involve a detailed exploration and analysis of a specific case. This may limit the feasibility of conducting multiple case studies or conducting case studies in a timely manner.
• Resource-intensive: Case studies may require significant resources, including time, funding, and expertise. This may limit the ability of researchers to conduct case studies in resource-constrained settings.

About the author

Muhammad Hassan

Researcher, Academic Writer, Web developer

You may also like

Questionnaire – Definition, Types, and Examples

Observational Research – Methods and Guide

Quantitative Research – Methods, Types and...

Qualitative Research Methods

Explanatory Research – Types, Methods, Guide

Survey Research – Types, Methods, Examples

The Ultimate Guide to Qualitative Research - Part 1: The Basics

• Introduction and overview
• What is qualitative research?
• What is qualitative data?
• Examples of qualitative data
• Qualitative vs. quantitative research
• Mixed methods
• Qualitative research preparation
• Theoretical perspective
• Theoretical framework
• Literature reviews

Research question

• Conceptual framework
• Conceptual vs. theoretical framework

Data collection

• Qualitative research methods
• Focus groups
• Observational research

What is a case study?

Applications for case study research, what is a good case study, process of case study design, benefits and limitations of case studies.

• Ethnographical research
• Ethical considerations
• Confidentiality and privacy
• Power dynamics
• Reflexivity

Case studies

Case studies are essential to qualitative research , offering a lens through which researchers can investigate complex phenomena within their real-life contexts. This chapter explores the concept, purpose, applications, examples, and types of case studies and provides guidance on how to conduct case study research effectively.

Whereas quantitative methods look at phenomena at scale, case study research looks at a concept or phenomenon in considerable detail. While analyzing a single case can help understand one perspective regarding the object of research inquiry, analyzing multiple cases can help obtain a more holistic sense of the topic or issue. Let's provide a basic definition of a case study, then explore its characteristics and role in the qualitative research process.

Definition of a case study

A case study in qualitative research is a strategy of inquiry that involves an in-depth investigation of a phenomenon within its real-world context. It provides researchers with the opportunity to acquire an in-depth understanding of intricate details that might not be as apparent or accessible through other methods of research. The specific case or cases being studied can be a single person, group, or organization – demarcating what constitutes a relevant case worth studying depends on the researcher and their research question .

Among qualitative research methods , a case study relies on multiple sources of evidence, such as documents, artifacts, interviews , or observations , to present a complete and nuanced understanding of the phenomenon under investigation. The objective is to illuminate the readers' understanding of the phenomenon beyond its abstract statistical or theoretical explanations.

Characteristics of case studies

Case studies typically possess a number of distinct characteristics that set them apart from other research methods. These characteristics include a focus on holistic description and explanation, flexibility in the design and data collection methods, reliance on multiple sources of evidence, and emphasis on the context in which the phenomenon occurs.

Furthermore, case studies can often involve a longitudinal examination of the case, meaning they study the case over a period of time. These characteristics allow case studies to yield comprehensive, in-depth, and richly contextualized insights about the phenomenon of interest.

The role of case studies in research

Case studies hold a unique position in the broader landscape of research methods aimed at theory development. They are instrumental when the primary research interest is to gain an intensive, detailed understanding of a phenomenon in its real-life context.

In addition, case studies can serve different purposes within research - they can be used for exploratory, descriptive, or explanatory purposes, depending on the research question and objectives. This flexibility and depth make case studies a valuable tool in the toolkit of qualitative researchers.

Remember, a well-conducted case study can offer a rich, insightful contribution to both academic and practical knowledge through theory development or theory verification, thus enhancing our understanding of complex phenomena in their real-world contexts.

What is the purpose of a case study?

Case study research aims for a more comprehensive understanding of phenomena, requiring various research methods to gather information for qualitative analysis . Ultimately, a case study can allow the researcher to gain insight into a particular object of inquiry and develop a theoretical framework relevant to the research inquiry.

Why use case studies in qualitative research?

Using case studies as a research strategy depends mainly on the nature of the research question and the researcher's access to the data.

Conducting case study research provides a level of detail and contextual richness that other research methods might not offer. They are beneficial when there's a need to understand complex social phenomena within their natural contexts.

The explanatory, exploratory, and descriptive roles of case studies

Case studies can take on various roles depending on the research objectives. They can be exploratory when the research aims to discover new phenomena or define new research questions; they are descriptive when the objective is to depict a phenomenon within its context in a detailed manner; and they can be explanatory if the goal is to understand specific relationships within the studied context. Thus, the versatility of case studies allows researchers to approach their topic from different angles, offering multiple ways to uncover and interpret the data .

The impact of case studies on knowledge development

Case studies play a significant role in knowledge development across various disciplines. Analysis of cases provides an avenue for researchers to explore phenomena within their context based on the collected data.

This can result in the production of rich, practical insights that can be instrumental in both theory-building and practice. Case studies allow researchers to delve into the intricacies and complexities of real-life situations, uncovering insights that might otherwise remain hidden.

Types of case studies

In qualitative research , a case study is not a one-size-fits-all approach. Depending on the nature of the research question and the specific objectives of the study, researchers might choose to use different types of case studies. These types differ in their focus, methodology, and the level of detail they provide about the phenomenon under investigation.

Understanding these types is crucial for selecting the most appropriate approach for your research project and effectively achieving your research goals. Let's briefly look at the main types of case studies.

Exploratory case studies

Exploratory case studies are typically conducted to develop a theory or framework around an understudied phenomenon. They can also serve as a precursor to a larger-scale research project. Exploratory case studies are useful when a researcher wants to identify the key issues or questions which can spur more extensive study or be used to develop propositions for further research. These case studies are characterized by flexibility, allowing researchers to explore various aspects of a phenomenon as they emerge, which can also form the foundation for subsequent studies.

Descriptive case studies

Descriptive case studies aim to provide a complete and accurate representation of a phenomenon or event within its context. These case studies are often based on an established theoretical framework, which guides how data is collected and analyzed. The researcher is concerned with describing the phenomenon in detail, as it occurs naturally, without trying to influence or manipulate it.

Explanatory case studies

Explanatory case studies are focused on explanation - they seek to clarify how or why certain phenomena occur. Often used in complex, real-life situations, they can be particularly valuable in clarifying causal relationships among concepts and understanding the interplay between different factors within a specific context.

Intrinsic, instrumental, and collective case studies

These three categories of case studies focus on the nature and purpose of the study. An intrinsic case study is conducted when a researcher has an inherent interest in the case itself. Instrumental case studies are employed when the case is used to provide insight into a particular issue or phenomenon. A collective case study, on the other hand, involves studying multiple cases simultaneously to investigate some general phenomena.

Each type of case study serves a different purpose and has its own strengths and challenges. The selection of the type should be guided by the research question and objectives, as well as the context and constraints of the research.

The flexibility, depth, and contextual richness offered by case studies make this approach an excellent research method for various fields of study. They enable researchers to investigate real-world phenomena within their specific contexts, capturing nuances that other research methods might miss. Across numerous fields, case studies provide valuable insights into complex issues.

Critical information systems research

Case studies provide a detailed understanding of the role and impact of information systems in different contexts. They offer a platform to explore how information systems are designed, implemented, and used and how they interact with various social, economic, and political factors. Case studies in this field often focus on examining the intricate relationship between technology, organizational processes, and user behavior, helping to uncover insights that can inform better system design and implementation.

Health research

Health research is another field where case studies are highly valuable. They offer a way to explore patient experiences, healthcare delivery processes, and the impact of various interventions in a real-world context.

Case studies can provide a deep understanding of a patient's journey, giving insights into the intricacies of disease progression, treatment effects, and the psychosocial aspects of health and illness.

Asthma research studies

Specifically within medical research, studies on asthma often employ case studies to explore the individual and environmental factors that influence asthma development, management, and outcomes. A case study can provide rich, detailed data about individual patients' experiences, from the triggers and symptoms they experience to the effectiveness of various management strategies. This can be crucial for developing patient-centered asthma care approaches.

Other fields

Apart from the fields mentioned, case studies are also extensively used in business and management research, education research, and political sciences, among many others. They provide an opportunity to delve into the intricacies of real-world situations, allowing for a comprehensive understanding of various phenomena.

Case studies, with their depth and contextual focus, offer unique insights across these varied fields. They allow researchers to illuminate the complexities of real-life situations, contributing to both theory and practice.

Whatever field you're in, ATLAS.ti puts your data to work for you

Download a free trial of ATLAS.ti to turn your data into insights.

Understanding the key elements of case study design is crucial for conducting rigorous and impactful case study research. A well-structured design guides the researcher through the process, ensuring that the study is methodologically sound and its findings are reliable and valid. The main elements of case study design include the research question , propositions, units of analysis, and the logic linking the data to the propositions.

The research question is the foundation of any research study. A good research question guides the direction of the study and informs the selection of the case, the methods of collecting data, and the analysis techniques. A well-formulated research question in case study research is typically clear, focused, and complex enough to merit further detailed examination of the relevant case(s).

Propositions

Propositions, though not necessary in every case study, provide a direction by stating what we might expect to find in the data collected. They guide how data is collected and analyzed by helping researchers focus on specific aspects of the case. They are particularly important in explanatory case studies, which seek to understand the relationships among concepts within the studied phenomenon.

Units of analysis

The unit of analysis refers to the case, or the main entity or entities that are being analyzed in the study. In case study research, the unit of analysis can be an individual, a group, an organization, a decision, an event, or even a time period. It's crucial to clearly define the unit of analysis, as it shapes the qualitative data analysis process by allowing the researcher to analyze a particular case and synthesize analysis across multiple case studies to draw conclusions.

Argumentation

This refers to the inferential model that allows researchers to draw conclusions from the data. The researcher needs to ensure that there is a clear link between the data, the propositions (if any), and the conclusions drawn. This argumentation is what enables the researcher to make valid and credible inferences about the phenomenon under study.

Understanding and carefully considering these elements in the design phase of a case study can significantly enhance the quality of the research. It can help ensure that the study is methodologically sound and its findings contribute meaningful insights about the case.

Ready to jumpstart your research with ATLAS.ti?

Conceptualize your research project with our intuitive data analysis interface. Download a free trial today.

Conducting a case study involves several steps, from defining the research question and selecting the case to collecting and analyzing data . This section outlines these key stages, providing a practical guide on how to conduct case study research.

Defining the research question

The first step in case study research is defining a clear, focused research question. This question should guide the entire research process, from case selection to analysis. It's crucial to ensure that the research question is suitable for a case study approach. Typically, such questions are exploratory or descriptive in nature and focus on understanding a phenomenon within its real-life context.

Selecting and defining the case

The selection of the case should be based on the research question and the objectives of the study. It involves choosing a unique example or a set of examples that provide rich, in-depth data about the phenomenon under investigation. After selecting the case, it's crucial to define it clearly, setting the boundaries of the case, including the time period and the specific context.

Previous research can help guide the case study design. When considering a case study, an example of a case could be taken from previous case study research and used to define cases in a new research inquiry. Considering recently published examples can help understand how to select and define cases effectively.

Developing a detailed case study protocol

A case study protocol outlines the procedures and general rules to be followed during the case study. This includes the data collection methods to be used, the sources of data, and the procedures for analysis. Having a detailed case study protocol ensures consistency and reliability in the study.

The protocol should also consider how to work with the people involved in the research context to grant the research team access to collecting data. As mentioned in previous sections of this guide, establishing rapport is an essential component of qualitative research as it shapes the overall potential for collecting and analyzing data.

Collecting data

Gathering data in case study research often involves multiple sources of evidence, including documents, archival records, interviews, observations, and physical artifacts. This allows for a comprehensive understanding of the case. The process for gathering data should be systematic and carefully documented to ensure the reliability and validity of the study.

Analyzing and interpreting data

The next step is analyzing the data. This involves organizing the data , categorizing it into themes or patterns , and interpreting these patterns to answer the research question. The analysis might also involve comparing the findings with prior research or theoretical propositions.

Writing the case study report

The final step is writing the case study report . This should provide a detailed description of the case, the data, the analysis process, and the findings. The report should be clear, organized, and carefully written to ensure that the reader can understand the case and the conclusions drawn from it.

Each of these steps is crucial in ensuring that the case study research is rigorous, reliable, and provides valuable insights about the case.

The type, depth, and quality of data in your study can significantly influence the validity and utility of the study. In case study research, data is usually collected from multiple sources to provide a comprehensive and nuanced understanding of the case. This section will outline the various methods of collecting data used in case study research and discuss considerations for ensuring the quality of the data.

Interviews are a common method of gathering data in case study research. They can provide rich, in-depth data about the perspectives, experiences, and interpretations of the individuals involved in the case. Interviews can be structured , semi-structured , or unstructured , depending on the research question and the degree of flexibility needed.

Observations

Observations involve the researcher observing the case in its natural setting, providing first-hand information about the case and its context. Observations can provide data that might not be revealed in interviews or documents, such as non-verbal cues or contextual information.

Documents and artifacts

Documents and archival records provide a valuable source of data in case study research. They can include reports, letters, memos, meeting minutes, email correspondence, and various public and private documents related to the case.

These records can provide historical context, corroborate evidence from other sources, and offer insights into the case that might not be apparent from interviews or observations.

Physical artifacts refer to any physical evidence related to the case, such as tools, products, or physical environments. These artifacts can provide tangible insights into the case, complementing the data gathered from other sources.

Ensuring the quality of data collection

Determining the quality of data in case study research requires careful planning and execution. It's crucial to ensure that the data is reliable, accurate, and relevant to the research question. This involves selecting appropriate methods of collecting data, properly training interviewers or observers, and systematically recording and storing the data. It also includes considering ethical issues related to collecting and handling data, such as obtaining informed consent and ensuring the privacy and confidentiality of the participants.

Data analysis

Analyzing case study research involves making sense of the rich, detailed data to answer the research question. This process can be challenging due to the volume and complexity of case study data. However, a systematic and rigorous approach to analysis can ensure that the findings are credible and meaningful. This section outlines the main steps and considerations in analyzing data in case study research.

Organizing the data

The first step in the analysis is organizing the data. This involves sorting the data into manageable sections, often according to the data source or the theme. This step can also involve transcribing interviews, digitizing physical artifacts, or organizing observational data.

Categorizing and coding the data

Once the data is organized, the next step is to categorize or code the data. This involves identifying common themes, patterns, or concepts in the data and assigning codes to relevant data segments. Coding can be done manually or with the help of software tools, and in either case, qualitative analysis software can greatly facilitate the entire coding process. Coding helps to reduce the data to a set of themes or categories that can be more easily analyzed.

Identifying patterns and themes

After coding the data, the researcher looks for patterns or themes in the coded data. This involves comparing and contrasting the codes and looking for relationships or patterns among them. The identified patterns and themes should help answer the research question.

Interpreting the data

Once patterns and themes have been identified, the next step is to interpret these findings. This involves explaining what the patterns or themes mean in the context of the research question and the case. This interpretation should be grounded in the data, but it can also involve drawing on theoretical concepts or prior research.

Verification of the data

The last step in the analysis is verification. This involves checking the accuracy and consistency of the analysis process and confirming that the findings are supported by the data. This can involve re-checking the original data, checking the consistency of codes, or seeking feedback from research participants or peers.

Like any research method , case study research has its strengths and limitations. Researchers must be aware of these, as they can influence the design, conduct, and interpretation of the study.

Understanding the strengths and limitations of case study research can also guide researchers in deciding whether this approach is suitable for their research question . This section outlines some of the key strengths and limitations of case study research.

Benefits include the following:

• Rich, detailed data: One of the main strengths of case study research is that it can generate rich, detailed data about the case. This can provide a deep understanding of the case and its context, which can be valuable in exploring complex phenomena.
• Flexibility: Case study research is flexible in terms of design , data collection , and analysis . A sufficient degree of flexibility allows the researcher to adapt the study according to the case and the emerging findings.
• Real-world context: Case study research involves studying the case in its real-world context, which can provide valuable insights into the interplay between the case and its context.
• Multiple sources of evidence: Case study research often involves collecting data from multiple sources , which can enhance the robustness and validity of the findings.

On the other hand, researchers should consider the following limitations:

• Generalizability: A common criticism of case study research is that its findings might not be generalizable to other cases due to the specificity and uniqueness of each case.
• Time and resource intensive: Case study research can be time and resource intensive due to the depth of the investigation and the amount of collected data.
• Complexity of analysis: The rich, detailed data generated in case study research can make analyzing the data challenging.
• Subjectivity: Given the nature of case study research, there may be a higher degree of subjectivity in interpreting the data , so researchers need to reflect on this and transparently convey to audiences how the research was conducted.

Being aware of these strengths and limitations can help researchers design and conduct case study research effectively and interpret and report the findings appropriately.

Ready to analyze your data with ATLAS.ti?

See how our intuitive software can draw key insights from your data with a free trial today.

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

What the Case Study Method Really Teaches

• Nitin Nohria

Seven meta-skills that stick even if the cases fade from memory.

It’s been 100 years since Harvard Business School began using the case study method. Beyond teaching specific subject matter, the case study method excels in instilling meta-skills in students. This article explains the importance of seven such skills: preparation, discernment, bias recognition, judgement, collaboration, curiosity, and self-confidence.

During my decade as dean of Harvard Business School, I spent hundreds of hours talking with our alumni. To enliven these conversations, I relied on a favorite question: “What was the most important thing you learned from your time in our MBA program?”

• Nitin Nohria is the George F. Baker Professor of Business Administration, Distinguished University Service Professor, and former dean of Harvard Business School.

Partner Center

• Open access
• Published: 27 June 2011

The case study approach

• Sarah Crowe 1 ,
• Kathrin Cresswell 2 ,
• Ann Robertson 2 ,
• Guro Huby 3 ,
• Anthony Avery 1 &
• Aziz Sheikh 2  

BMC Medical Research Methodology volume  11 , Article number:  100 ( 2011 ) Cite this article

776k Accesses

1038 Citations

37 Altmetric

Metrics details

The case study approach allows in-depth, multi-faceted explorations of complex issues in their real-life settings. The value of the case study approach is well recognised in the fields of business, law and policy, but somewhat less so in health services research. Based on our experiences of conducting several health-related case studies, we reflect on the different types of case study design, the specific research questions this approach can help answer, the data sources that tend to be used, and the particular advantages and disadvantages of employing this methodological approach. The paper concludes with key pointers to aid those designing and appraising proposals for conducting case study research, and a checklist to help readers assess the quality of case study reports.

Peer Review reports

Introduction

The case study approach is particularly useful to employ when there is a need to obtain an in-depth appreciation of an issue, event or phenomenon of interest, in its natural real-life context. Our aim in writing this piece is to provide insights into when to consider employing this approach and an overview of key methodological considerations in relation to the design, planning, analysis, interpretation and reporting of case studies.

The illustrative 'grand round', 'case report' and 'case series' have a long tradition in clinical practice and research. Presenting detailed critiques, typically of one or more patients, aims to provide insights into aspects of the clinical case and, in doing so, illustrate broader lessons that may be learnt. In research, the conceptually-related case study approach can be used, for example, to describe in detail a patient's episode of care, explore professional attitudes to and experiences of a new policy initiative or service development or more generally to 'investigate contemporary phenomena within its real-life context' [ 1 ]. Based on our experiences of conducting a range of case studies, we reflect on when to consider using this approach, discuss the key steps involved and illustrate, with examples, some of the practical challenges of attaining an in-depth understanding of a 'case' as an integrated whole. In keeping with previously published work, we acknowledge the importance of theory to underpin the design, selection, conduct and interpretation of case studies[ 2 ]. In so doing, we make passing reference to the different epistemological approaches used in case study research by key theoreticians and methodologists in this field of enquiry.

This paper is structured around the following main questions: What is a case study? What are case studies used for? How are case studies conducted? What are the potential pitfalls and how can these be avoided? We draw in particular on four of our own recently published examples of case studies (see Tables 1 , 2 , 3 and 4 ) and those of others to illustrate our discussion[ 3 – 7 ].

What is a case study?

A case study is a research approach that is used to generate an in-depth, multi-faceted understanding of a complex issue in its real-life context. It is an established research design that is used extensively in a wide variety of disciplines, particularly in the social sciences. A case study can be defined in a variety of ways (Table 5 ), the central tenet being the need to explore an event or phenomenon in depth and in its natural context. It is for this reason sometimes referred to as a "naturalistic" design; this is in contrast to an "experimental" design (such as a randomised controlled trial) in which the investigator seeks to exert control over and manipulate the variable(s) of interest.

Stake's work has been particularly influential in defining the case study approach to scientific enquiry. He has helpfully characterised three main types of case study: intrinsic , instrumental and collective [ 8 ]. An intrinsic case study is typically undertaken to learn about a unique phenomenon. The researcher should define the uniqueness of the phenomenon, which distinguishes it from all others. In contrast, the instrumental case study uses a particular case (some of which may be better than others) to gain a broader appreciation of an issue or phenomenon. The collective case study involves studying multiple cases simultaneously or sequentially in an attempt to generate a still broader appreciation of a particular issue.

These are however not necessarily mutually exclusive categories. In the first of our examples (Table 1 ), we undertook an intrinsic case study to investigate the issue of recruitment of minority ethnic people into the specific context of asthma research studies, but it developed into a instrumental case study through seeking to understand the issue of recruitment of these marginalised populations more generally, generating a number of the findings that are potentially transferable to other disease contexts[ 3 ]. In contrast, the other three examples (see Tables 2 , 3 and 4 ) employed collective case study designs to study the introduction of workforce reconfiguration in primary care, the implementation of electronic health records into hospitals, and to understand the ways in which healthcare students learn about patient safety considerations[ 4 – 6 ]. Although our study focusing on the introduction of General Practitioners with Specialist Interests (Table 2 ) was explicitly collective in design (four contrasting primary care organisations were studied), is was also instrumental in that this particular professional group was studied as an exemplar of the more general phenomenon of workforce redesign[ 4 ].

What are case studies used for?

According to Yin, case studies can be used to explain, describe or explore events or phenomena in the everyday contexts in which they occur[ 1 ]. These can, for example, help to understand and explain causal links and pathways resulting from a new policy initiative or service development (see Tables 2 and 3 , for example)[ 1 ]. In contrast to experimental designs, which seek to test a specific hypothesis through deliberately manipulating the environment (like, for example, in a randomised controlled trial giving a new drug to randomly selected individuals and then comparing outcomes with controls),[ 9 ] the case study approach lends itself well to capturing information on more explanatory ' how ', 'what' and ' why ' questions, such as ' how is the intervention being implemented and received on the ground?'. The case study approach can offer additional insights into what gaps exist in its delivery or why one implementation strategy might be chosen over another. This in turn can help develop or refine theory, as shown in our study of the teaching of patient safety in undergraduate curricula (Table 4 )[ 6 , 10 ]. Key questions to consider when selecting the most appropriate study design are whether it is desirable or indeed possible to undertake a formal experimental investigation in which individuals and/or organisations are allocated to an intervention or control arm? Or whether the wish is to obtain a more naturalistic understanding of an issue? The former is ideally studied using a controlled experimental design, whereas the latter is more appropriately studied using a case study design.

Case studies may be approached in different ways depending on the epistemological standpoint of the researcher, that is, whether they take a critical (questioning one's own and others' assumptions), interpretivist (trying to understand individual and shared social meanings) or positivist approach (orientating towards the criteria of natural sciences, such as focusing on generalisability considerations) (Table 6 ). Whilst such a schema can be conceptually helpful, it may be appropriate to draw on more than one approach in any case study, particularly in the context of conducting health services research. Doolin has, for example, noted that in the context of undertaking interpretative case studies, researchers can usefully draw on a critical, reflective perspective which seeks to take into account the wider social and political environment that has shaped the case[ 11 ].

How are case studies conducted?

Here, we focus on the main stages of research activity when planning and undertaking a case study; the crucial stages are: defining the case; selecting the case(s); collecting and analysing the data; interpreting data; and reporting the findings.

Defining the case

Carefully formulated research question(s), informed by the existing literature and a prior appreciation of the theoretical issues and setting(s), are all important in appropriately and succinctly defining the case[ 8 , 12 ]. Crucially, each case should have a pre-defined boundary which clarifies the nature and time period covered by the case study (i.e. its scope, beginning and end), the relevant social group, organisation or geographical area of interest to the investigator, the types of evidence to be collected, and the priorities for data collection and analysis (see Table 7 )[ 1 ]. A theory driven approach to defining the case may help generate knowledge that is potentially transferable to a range of clinical contexts and behaviours; using theory is also likely to result in a more informed appreciation of, for example, how and why interventions have succeeded or failed[ 13 ].

For example, in our evaluation of the introduction of electronic health records in English hospitals (Table 3 ), we defined our cases as the NHS Trusts that were receiving the new technology[ 5 ]. Our focus was on how the technology was being implemented. However, if the primary research interest had been on the social and organisational dimensions of implementation, we might have defined our case differently as a grouping of healthcare professionals (e.g. doctors and/or nurses). The precise beginning and end of the case may however prove difficult to define. Pursuing this same example, when does the process of implementation and adoption of an electronic health record system really begin or end? Such judgements will inevitably be influenced by a range of factors, including the research question, theory of interest, the scope and richness of the gathered data and the resources available to the research team.

Selecting the case(s)

The decision on how to select the case(s) to study is a very important one that merits some reflection. In an intrinsic case study, the case is selected on its own merits[ 8 ]. The case is selected not because it is representative of other cases, but because of its uniqueness, which is of genuine interest to the researchers. This was, for example, the case in our study of the recruitment of minority ethnic participants into asthma research (Table 1 ) as our earlier work had demonstrated the marginalisation of minority ethnic people with asthma, despite evidence of disproportionate asthma morbidity[ 14 , 15 ]. In another example of an intrinsic case study, Hellstrom et al.[ 16 ] studied an elderly married couple living with dementia to explore how dementia had impacted on their understanding of home, their everyday life and their relationships.

For an instrumental case study, selecting a "typical" case can work well[ 8 ]. In contrast to the intrinsic case study, the particular case which is chosen is of less importance than selecting a case that allows the researcher to investigate an issue or phenomenon. For example, in order to gain an understanding of doctors' responses to health policy initiatives, Som undertook an instrumental case study interviewing clinicians who had a range of responsibilities for clinical governance in one NHS acute hospital trust[ 17 ]. Sampling a "deviant" or "atypical" case may however prove even more informative, potentially enabling the researcher to identify causal processes, generate hypotheses and develop theory.

In collective or multiple case studies, a number of cases are carefully selected. This offers the advantage of allowing comparisons to be made across several cases and/or replication. Choosing a "typical" case may enable the findings to be generalised to theory (i.e. analytical generalisation) or to test theory by replicating the findings in a second or even a third case (i.e. replication logic)[ 1 ]. Yin suggests two or three literal replications (i.e. predicting similar results) if the theory is straightforward and five or more if the theory is more subtle. However, critics might argue that selecting 'cases' in this way is insufficiently reflexive and ill-suited to the complexities of contemporary healthcare organisations.

The selected case study site(s) should allow the research team access to the group of individuals, the organisation, the processes or whatever else constitutes the chosen unit of analysis for the study. Access is therefore a central consideration; the researcher needs to come to know the case study site(s) well and to work cooperatively with them. Selected cases need to be not only interesting but also hospitable to the inquiry [ 8 ] if they are to be informative and answer the research question(s). Case study sites may also be pre-selected for the researcher, with decisions being influenced by key stakeholders. For example, our selection of case study sites in the evaluation of the implementation and adoption of electronic health record systems (see Table 3 ) was heavily influenced by NHS Connecting for Health, the government agency that was responsible for overseeing the National Programme for Information Technology (NPfIT)[ 5 ]. This prominent stakeholder had already selected the NHS sites (through a competitive bidding process) to be early adopters of the electronic health record systems and had negotiated contracts that detailed the deployment timelines.

It is also important to consider in advance the likely burden and risks associated with participation for those who (or the site(s) which) comprise the case study. Of particular importance is the obligation for the researcher to think through the ethical implications of the study (e.g. the risk of inadvertently breaching anonymity or confidentiality) and to ensure that potential participants/participating sites are provided with sufficient information to make an informed choice about joining the study. The outcome of providing this information might be that the emotive burden associated with participation, or the organisational disruption associated with supporting the fieldwork, is considered so high that the individuals or sites decide against participation.

In our example of evaluating implementations of electronic health record systems, given the restricted number of early adopter sites available to us, we sought purposively to select a diverse range of implementation cases among those that were available[ 5 ]. We chose a mixture of teaching, non-teaching and Foundation Trust hospitals, and examples of each of the three electronic health record systems procured centrally by the NPfIT. At one recruited site, it quickly became apparent that access was problematic because of competing demands on that organisation. Recognising the importance of full access and co-operative working for generating rich data, the research team decided not to pursue work at that site and instead to focus on other recruited sites.

Collecting the data

In order to develop a thorough understanding of the case, the case study approach usually involves the collection of multiple sources of evidence, using a range of quantitative (e.g. questionnaires, audits and analysis of routinely collected healthcare data) and more commonly qualitative techniques (e.g. interviews, focus groups and observations). The use of multiple sources of data (data triangulation) has been advocated as a way of increasing the internal validity of a study (i.e. the extent to which the method is appropriate to answer the research question)[ 8 , 18 – 21 ]. An underlying assumption is that data collected in different ways should lead to similar conclusions, and approaching the same issue from different angles can help develop a holistic picture of the phenomenon (Table 2 )[ 4 ].

Brazier and colleagues used a mixed-methods case study approach to investigate the impact of a cancer care programme[ 22 ]. Here, quantitative measures were collected with questionnaires before, and five months after, the start of the intervention which did not yield any statistically significant results. Qualitative interviews with patients however helped provide an insight into potentially beneficial process-related aspects of the programme, such as greater, perceived patient involvement in care. The authors reported how this case study approach provided a number of contextual factors likely to influence the effectiveness of the intervention and which were not likely to have been obtained from quantitative methods alone.

In collective or multiple case studies, data collection needs to be flexible enough to allow a detailed description of each individual case to be developed (e.g. the nature of different cancer care programmes), before considering the emerging similarities and differences in cross-case comparisons (e.g. to explore why one programme is more effective than another). It is important that data sources from different cases are, where possible, broadly comparable for this purpose even though they may vary in nature and depth.

Analysing, interpreting and reporting case studies

Making sense and offering a coherent interpretation of the typically disparate sources of data (whether qualitative alone or together with quantitative) is far from straightforward. Repeated reviewing and sorting of the voluminous and detail-rich data are integral to the process of analysis. In collective case studies, it is helpful to analyse data relating to the individual component cases first, before making comparisons across cases. Attention needs to be paid to variations within each case and, where relevant, the relationship between different causes, effects and outcomes[ 23 ]. Data will need to be organised and coded to allow the key issues, both derived from the literature and emerging from the dataset, to be easily retrieved at a later stage. An initial coding frame can help capture these issues and can be applied systematically to the whole dataset with the aid of a qualitative data analysis software package.

The Framework approach is a practical approach, comprising of five stages (familiarisation; identifying a thematic framework; indexing; charting; mapping and interpretation) , to managing and analysing large datasets particularly if time is limited, as was the case in our study of recruitment of South Asians into asthma research (Table 1 )[ 3 , 24 ]. Theoretical frameworks may also play an important role in integrating different sources of data and examining emerging themes. For example, we drew on a socio-technical framework to help explain the connections between different elements - technology; people; and the organisational settings within which they worked - in our study of the introduction of electronic health record systems (Table 3 )[ 5 ]. Our study of patient safety in undergraduate curricula drew on an evaluation-based approach to design and analysis, which emphasised the importance of the academic, organisational and practice contexts through which students learn (Table 4 )[ 6 ].

Case study findings can have implications both for theory development and theory testing. They may establish, strengthen or weaken historical explanations of a case and, in certain circumstances, allow theoretical (as opposed to statistical) generalisation beyond the particular cases studied[ 12 ]. These theoretical lenses should not, however, constitute a strait-jacket and the cases should not be "forced to fit" the particular theoretical framework that is being employed.

When reporting findings, it is important to provide the reader with enough contextual information to understand the processes that were followed and how the conclusions were reached. In a collective case study, researchers may choose to present the findings from individual cases separately before amalgamating across cases. Care must be taken to ensure the anonymity of both case sites and individual participants (if agreed in advance) by allocating appropriate codes or withholding descriptors. In the example given in Table 3 , we decided against providing detailed information on the NHS sites and individual participants in order to avoid the risk of inadvertent disclosure of identities[ 5 , 25 ].

What are the potential pitfalls and how can these be avoided?

The case study approach is, as with all research, not without its limitations. When investigating the formal and informal ways undergraduate students learn about patient safety (Table 4 ), for example, we rapidly accumulated a large quantity of data. The volume of data, together with the time restrictions in place, impacted on the depth of analysis that was possible within the available resources. This highlights a more general point of the importance of avoiding the temptation to collect as much data as possible; adequate time also needs to be set aside for data analysis and interpretation of what are often highly complex datasets.

Case study research has sometimes been criticised for lacking scientific rigour and providing little basis for generalisation (i.e. producing findings that may be transferable to other settings)[ 1 ]. There are several ways to address these concerns, including: the use of theoretical sampling (i.e. drawing on a particular conceptual framework); respondent validation (i.e. participants checking emerging findings and the researcher's interpretation, and providing an opinion as to whether they feel these are accurate); and transparency throughout the research process (see Table 8 )[ 8 , 18 – 21 , 23 , 26 ]. Transparency can be achieved by describing in detail the steps involved in case selection, data collection, the reasons for the particular methods chosen, and the researcher's background and level of involvement (i.e. being explicit about how the researcher has influenced data collection and interpretation). Seeking potential, alternative explanations, and being explicit about how interpretations and conclusions were reached, help readers to judge the trustworthiness of the case study report. Stake provides a critique checklist for a case study report (Table 9 )[ 8 ].

Conclusions

The case study approach allows, amongst other things, critical events, interventions, policy developments and programme-based service reforms to be studied in detail in a real-life context. It should therefore be considered when an experimental design is either inappropriate to answer the research questions posed or impossible to undertake. Considering the frequency with which implementations of innovations are now taking place in healthcare settings and how well the case study approach lends itself to in-depth, complex health service research, we believe this approach should be more widely considered by researchers. Though inherently challenging, the research case study can, if carefully conceptualised and thoughtfully undertaken and reported, yield powerful insights into many important aspects of health and healthcare delivery.

Yin RK: Case study research, design and method. 2009, London: Sage Publications Ltd., 4

Google Scholar  

Keen J, Packwood T: Qualitative research; case study evaluation. BMJ. 1995, 311: 444-446.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Sheikh A, Halani L, Bhopal R, Netuveli G, Partridge M, Car J, et al: Facilitating the Recruitment of Minority Ethnic People into Research: Qualitative Case Study of South Asians and Asthma. PLoS Med. 2009, 6 (10): 1-11.

Article   Google Scholar  

Pinnock H, Huby G, Powell A, Kielmann T, Price D, Williams S, et al: The process of planning, development and implementation of a General Practitioner with a Special Interest service in Primary Care Organisations in England and Wales: a comparative prospective case study. Report for the National Co-ordinating Centre for NHS Service Delivery and Organisation R&D (NCCSDO). 2008, [ http://www.sdo.nihr.ac.uk/files/project/99-final-report.pdf ]

Robertson A, Cresswell K, Takian A, Petrakaki D, Crowe S, Cornford T, et al: Prospective evaluation of the implementation and adoption of NHS Connecting for Health's national electronic health record in secondary care in England: interim findings. BMJ. 2010, 41: c4564-

Pearson P, Steven A, Howe A, Sheikh A, Ashcroft D, Smith P, the Patient Safety Education Study Group: Learning about patient safety: organisational context and culture in the education of healthcare professionals. J Health Serv Res Policy. 2010, 15: 4-10. 10.1258/jhsrp.2009.009052.

Article   PubMed   Google Scholar  

van Harten WH, Casparie TF, Fisscher OA: The evaluation of the introduction of a quality management system: a process-oriented case study in a large rehabilitation hospital. Health Policy. 2002, 60 (1): 17-37. 10.1016/S0168-8510(01)00187-7.

Stake RE: The art of case study research. 1995, London: Sage Publications Ltd.

Sheikh A, Smeeth L, Ashcroft R: Randomised controlled trials in primary care: scope and application. Br J Gen Pract. 2002, 52 (482): 746-51.

PubMed   PubMed Central   Google Scholar  

King G, Keohane R, Verba S: Designing Social Inquiry. 1996, Princeton: Princeton University Press

Doolin B: Information technology as disciplinary technology: being critical in interpretative research on information systems. Journal of Information Technology. 1998, 13: 301-311. 10.1057/jit.1998.8.

George AL, Bennett A: Case studies and theory development in the social sciences. 2005, Cambridge, MA: MIT Press

Eccles M, the Improved Clinical Effectiveness through Behavioural Research Group (ICEBeRG): Designing theoretically-informed implementation interventions. Implementation Science. 2006, 1: 1-8. 10.1186/1748-5908-1-1.

Article   PubMed Central   Google Scholar  

Netuveli G, Hurwitz B, Levy M, Fletcher M, Barnes G, Durham SR, Sheikh A: Ethnic variations in UK asthma frequency, morbidity, and health-service use: a systematic review and meta-analysis. Lancet. 2005, 365 (9456): 312-7.

Sheikh A, Panesar SS, Lasserson T, Netuveli G: Recruitment of ethnic minorities to asthma studies. Thorax. 2004, 59 (7): 634-

CAS   PubMed   PubMed Central   Google Scholar  

Hellström I, Nolan M, Lundh U: 'We do things together': A case study of 'couplehood' in dementia. Dementia. 2005, 4: 7-22. 10.1177/1471301205049188.

Som CV: Nothing seems to have changed, nothing seems to be changing and perhaps nothing will change in the NHS: doctors' response to clinical governance. International Journal of Public Sector Management. 2005, 18: 463-477. 10.1108/09513550510608903.

Lincoln Y, Guba E: Naturalistic inquiry. 1985, Newbury Park: Sage Publications

Barbour RS: Checklists for improving rigour in qualitative research: a case of the tail wagging the dog?. BMJ. 2001, 322: 1115-1117. 10.1136/bmj.322.7294.1115.

Mays N, Pope C: Qualitative research in health care: Assessing quality in qualitative research. BMJ. 2000, 320: 50-52. 10.1136/bmj.320.7226.50.

Mason J: Qualitative researching. 2002, London: Sage

Brazier A, Cooke K, Moravan V: Using Mixed Methods for Evaluating an Integrative Approach to Cancer Care: A Case Study. Integr Cancer Ther. 2008, 7: 5-17. 10.1177/1534735407313395.

Miles MB, Huberman M: Qualitative data analysis: an expanded sourcebook. 1994, CA: Sage Publications Inc., 2

Pope C, Ziebland S, Mays N: Analysing qualitative data. Qualitative research in health care. BMJ. 2000, 320: 114-116. 10.1136/bmj.320.7227.114.

Cresswell KM, Worth A, Sheikh A: Actor-Network Theory and its role in understanding the implementation of information technology developments in healthcare. BMC Med Inform Decis Mak. 2010, 10 (1): 67-10.1186/1472-6947-10-67.

Article   PubMed   PubMed Central   Google Scholar  

Malterud K: Qualitative research: standards, challenges, and guidelines. Lancet. 2001, 358: 483-488. 10.1016/S0140-6736(01)05627-6.

Article   CAS   PubMed   Google Scholar  

Yin R: Case study research: design and methods. 1994, Thousand Oaks, CA: Sage Publishing, 2

Yin R: Enhancing the quality of case studies in health services research. Health Serv Res. 1999, 34: 1209-1224.

Green J, Thorogood N: Qualitative methods for health research. 2009, Los Angeles: Sage, 2

Howcroft D, Trauth E: Handbook of Critical Information Systems Research, Theory and Application. 2005, Cheltenham, UK: Northampton, MA, USA: Edward Elgar

Book   Google Scholar  

Blakie N: Approaches to Social Enquiry. 1993, Cambridge: Polity Press

Doolin B: Power and resistance in the implementation of a medical management information system. Info Systems J. 2004, 14: 343-362. 10.1111/j.1365-2575.2004.00176.x.

Bloomfield BP, Best A: Management consultants: systems development, power and the translation of problems. Sociological Review. 1992, 40: 533-560.

Shanks G, Parr A: Positivist, single case study research in information systems: A critical analysis. Proceedings of the European Conference on Information Systems. 2003, Naples

Pre-publication history

The pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2288/11/100/prepub

Download references

Acknowledgements

We are grateful to the participants and colleagues who contributed to the individual case studies that we have drawn on. This work received no direct funding, but it has been informed by projects funded by Asthma UK, the NHS Service Delivery Organisation, NHS Connecting for Health Evaluation Programme, and Patient Safety Research Portfolio. We would also like to thank the expert reviewers for their insightful and constructive feedback. Our thanks are also due to Dr. Allison Worth who commented on an earlier draft of this manuscript.

Author information

Authors and affiliations.

Division of Primary Care, The University of Nottingham, Nottingham, UK

Sarah Crowe & Anthony Avery

Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, UK

Kathrin Cresswell, Ann Robertson & Aziz Sheikh

School of Health in Social Science, The University of Edinburgh, Edinburgh, UK

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Sarah Crowe .

Additional information

Competing interests.

The authors declare that they have no competing interests.

Authors' contributions

AS conceived this article. SC, KC and AR wrote this paper with GH, AA and AS all commenting on various drafts. SC and AS are guarantors.

Rights and permissions

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and permissions

About this article

Cite this article.

Crowe, S., Cresswell, K., Robertson, A. et al. The case study approach. BMC Med Res Methodol 11 , 100 (2011). https://doi.org/10.1186/1471-2288-11-100

Download citation

Received : 29 November 2010

Accepted : 27 June 2011

Published : 27 June 2011

DOI : https://doi.org/10.1186/1471-2288-11-100

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Case Study Approach
• Electronic Health Record System
• Case Study Design
• Case Study Site
• Case Study Report

BMC Medical Research Methodology

ISSN: 1471-2288

• General enquiries: [email protected]

Organizing Your Social Sciences Research Assignments

• Annotated Bibliography
• Analyzing a Scholarly Journal Article
• Group Presentations
• Dealing with Nervousness
• Using Visual Aids
• Grading Someone Else's Paper
• Types of Structured Group Activities
• Group Project Survival Skills
• Leading a Class Discussion
• Multiple Book Review Essay
• Reviewing Collected Works
• Writing a Case Analysis Paper
• Writing a Case Study
• About Informed Consent
• Writing Field Notes
• Writing a Policy Memo
• Writing a Reflective Paper
• Writing a Research Proposal
• Generative AI and Writing
• Acknowledgments

A case study research paper examines a person, place, event, condition, phenomenon, or other type of subject of analysis in order to extrapolate  key themes and results that help predict future trends, illuminate previously hidden issues that can be applied to practice, and/or provide a means for understanding an important research problem with greater clarity. A case study research paper usually examines a single subject of analysis, but case study papers can also be designed as a comparative investigation that shows relationships between two or more subjects. The methods used to study a case can rest within a quantitative, qualitative, or mixed-method investigative paradigm.

Case Studies. Writing@CSU. Colorado State University; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010 ; “What is a Case Study?” In Swanborn, Peter G. Case Study Research: What, Why and How? London: SAGE, 2010.

How to Approach Writing a Case Study Research Paper

General information about how to choose a topic to investigate can be found under the " Choosing a Research Problem " tab in the Organizing Your Social Sciences Research Paper writing guide. Review this page because it may help you identify a subject of analysis that can be investigated using a case study design.

However, identifying a case to investigate involves more than choosing the research problem . A case study encompasses a problem contextualized around the application of in-depth analysis, interpretation, and discussion, often resulting in specific recommendations for action or for improving existing conditions. As Seawright and Gerring note, practical considerations such as time and access to information can influence case selection, but these issues should not be the sole factors used in describing the methodological justification for identifying a particular case to study. Given this, selecting a case includes considering the following:

• The case represents an unusual or atypical example of a research problem that requires more in-depth analysis? Cases often represent a topic that rests on the fringes of prior investigations because the case may provide new ways of understanding the research problem. For example, if the research problem is to identify strategies to improve policies that support girl's access to secondary education in predominantly Muslim nations, you could consider using Azerbaijan as a case study rather than selecting a more obvious nation in the Middle East. Doing so may reveal important new insights into recommending how governments in other predominantly Muslim nations can formulate policies that support improved access to education for girls.
• The case provides important insight or illuminate a previously hidden problem? In-depth analysis of a case can be based on the hypothesis that the case study will reveal trends or issues that have not been exposed in prior research or will reveal new and important implications for practice. For example, anecdotal evidence may suggest drug use among homeless veterans is related to their patterns of travel throughout the day. Assuming prior studies have not looked at individual travel choices as a way to study access to illicit drug use, a case study that observes a homeless veteran could reveal how issues of personal mobility choices facilitate regular access to illicit drugs. Note that it is important to conduct a thorough literature review to ensure that your assumption about the need to reveal new insights or previously hidden problems is valid and evidence-based.
• The case challenges and offers a counter-point to prevailing assumptions? Over time, research on any given topic can fall into a trap of developing assumptions based on outdated studies that are still applied to new or changing conditions or the idea that something should simply be accepted as "common sense," even though the issue has not been thoroughly tested in current practice. A case study analysis may offer an opportunity to gather evidence that challenges prevailing assumptions about a research problem and provide a new set of recommendations applied to practice that have not been tested previously. For example, perhaps there has been a long practice among scholars to apply a particular theory in explaining the relationship between two subjects of analysis. Your case could challenge this assumption by applying an innovative theoretical framework [perhaps borrowed from another discipline] to explore whether this approach offers new ways of understanding the research problem. Taking a contrarian stance is one of the most important ways that new knowledge and understanding develops from existing literature.
• The case provides an opportunity to pursue action leading to the resolution of a problem? Another way to think about choosing a case to study is to consider how the results from investigating a particular case may result in findings that reveal ways in which to resolve an existing or emerging problem. For example, studying the case of an unforeseen incident, such as a fatal accident at a railroad crossing, can reveal hidden issues that could be applied to preventative measures that contribute to reducing the chance of accidents in the future. In this example, a case study investigating the accident could lead to a better understanding of where to strategically locate additional signals at other railroad crossings so as to better warn drivers of an approaching train, particularly when visibility is hindered by heavy rain, fog, or at night.
• The case offers a new direction in future research? A case study can be used as a tool for an exploratory investigation that highlights the need for further research about the problem. A case can be used when there are few studies that help predict an outcome or that establish a clear understanding about how best to proceed in addressing a problem. For example, after conducting a thorough literature review [very important!], you discover that little research exists showing the ways in which women contribute to promoting water conservation in rural communities of east central Africa. A case study of how women contribute to saving water in a rural village of Uganda can lay the foundation for understanding the need for more thorough research that documents how women in their roles as cooks and family caregivers think about water as a valuable resource within their community. This example of a case study could also point to the need for scholars to build new theoretical frameworks around the topic [e.g., applying feminist theories of work and family to the issue of water conservation].

Eisenhardt, Kathleen M. “Building Theories from Case Study Research.” Academy of Management Review 14 (October 1989): 532-550; Emmel, Nick. Sampling and Choosing Cases in Qualitative Research: A Realist Approach . Thousand Oaks, CA: SAGE Publications, 2013; Gerring, John. “What Is a Case Study and What Is It Good for?” American Political Science Review 98 (May 2004): 341-354; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Seawright, Jason and John Gerring. "Case Selection Techniques in Case Study Research." Political Research Quarterly 61 (June 2008): 294-308.

Structure and Writing Style

The purpose of a paper in the social sciences designed around a case study is to thoroughly investigate a subject of analysis in order to reveal a new understanding about the research problem and, in so doing, contributing new knowledge to what is already known from previous studies. In applied social sciences disciplines [e.g., education, social work, public administration, etc.], case studies may also be used to reveal best practices, highlight key programs, or investigate interesting aspects of professional work.

In general, the structure of a case study research paper is not all that different from a standard college-level research paper. However, there are subtle differences you should be aware of. Here are the key elements to organizing and writing a case study research paper.

I.  Introduction

As with any research paper, your introduction should serve as a roadmap for your readers to ascertain the scope and purpose of your study . The introduction to a case study research paper, however, should not only describe the research problem and its significance, but you should also succinctly describe why the case is being used and how it relates to addressing the problem. The two elements should be linked. With this in mind, a good introduction answers these four questions:

• What is being studied? Describe the research problem and describe the subject of analysis [the case] you have chosen to address the problem. Explain how they are linked and what elements of the case will help to expand knowledge and understanding about the problem.
• Why is this topic important to investigate? Describe the significance of the research problem and state why a case study design and the subject of analysis that the paper is designed around is appropriate in addressing the problem.
• What did we know about this topic before I did this study? Provide background that helps lead the reader into the more in-depth literature review to follow. If applicable, summarize prior case study research applied to the research problem and why it fails to adequately address the problem. Describe why your case will be useful. If no prior case studies have been used to address the research problem, explain why you have selected this subject of analysis.
• How will this study advance new knowledge or new ways of understanding? Explain why your case study will be suitable in helping to expand knowledge and understanding about the research problem.

Each of these questions should be addressed in no more than a few paragraphs. Exceptions to this can be when you are addressing a complex research problem or subject of analysis that requires more in-depth background information.

II.  Literature Review

The literature review for a case study research paper is generally structured the same as it is for any college-level research paper. The difference, however, is that the literature review is focused on providing background information and  enabling historical interpretation of the subject of analysis in relation to the research problem the case is intended to address . This includes synthesizing studies that help to:

• Place relevant works in the context of their contribution to understanding the case study being investigated . This would involve summarizing studies that have used a similar subject of analysis to investigate the research problem. If there is literature using the same or a very similar case to study, you need to explain why duplicating past research is important [e.g., conditions have changed; prior studies were conducted long ago, etc.].
• Describe the relationship each work has to the others under consideration that informs the reader why this case is applicable . Your literature review should include a description of any works that support using the case to investigate the research problem and the underlying research questions.
• Identify new ways to interpret prior research using the case study . If applicable, review any research that has examined the research problem using a different research design. Explain how your use of a case study design may reveal new knowledge or a new perspective or that can redirect research in an important new direction.
• Resolve conflicts amongst seemingly contradictory previous studies . This refers to synthesizing any literature that points to unresolved issues of concern about the research problem and describing how the subject of analysis that forms the case study can help resolve these existing contradictions.
• Point the way in fulfilling a need for additional research . Your review should examine any literature that lays a foundation for understanding why your case study design and the subject of analysis around which you have designed your study may reveal a new way of approaching the research problem or offer a perspective that points to the need for additional research.
• Expose any gaps that exist in the literature that the case study could help to fill . Summarize any literature that not only shows how your subject of analysis contributes to understanding the research problem, but how your case contributes to a new way of understanding the problem that prior research has failed to do.
• Locate your own research within the context of existing literature [very important!] . Collectively, your literature review should always place your case study within the larger domain of prior research about the problem. The overarching purpose of reviewing pertinent literature in a case study paper is to demonstrate that you have thoroughly identified and synthesized prior studies in relation to explaining the relevance of the case in addressing the research problem.

III.  Method

In this section, you explain why you selected a particular case [i.e., subject of analysis] and the strategy you used to identify and ultimately decide that your case was appropriate in addressing the research problem. The way you describe the methods used varies depending on the type of subject of analysis that constitutes your case study.

If your subject of analysis is an incident or event . In the social and behavioral sciences, the event or incident that represents the case to be studied is usually bounded by time and place, with a clear beginning and end and with an identifiable location or position relative to its surroundings. The subject of analysis can be a rare or critical event or it can focus on a typical or regular event. The purpose of studying a rare event is to illuminate new ways of thinking about the broader research problem or to test a hypothesis. Critical incident case studies must describe the method by which you identified the event and explain the process by which you determined the validity of this case to inform broader perspectives about the research problem or to reveal new findings. However, the event does not have to be a rare or uniquely significant to support new thinking about the research problem or to challenge an existing hypothesis. For example, Walo, Bull, and Breen conducted a case study to identify and evaluate the direct and indirect economic benefits and costs of a local sports event in the City of Lismore, New South Wales, Australia. The purpose of their study was to provide new insights from measuring the impact of a typical local sports event that prior studies could not measure well because they focused on large "mega-events." Whether the event is rare or not, the methods section should include an explanation of the following characteristics of the event: a) when did it take place; b) what were the underlying circumstances leading to the event; and, c) what were the consequences of the event in relation to the research problem.

If your subject of analysis is a person. Explain why you selected this particular individual to be studied and describe what experiences they have had that provide an opportunity to advance new understandings about the research problem. Mention any background about this person which might help the reader understand the significance of their experiences that make them worthy of study. This includes describing the relationships this person has had with other people, institutions, and/or events that support using them as the subject for a case study research paper. It is particularly important to differentiate the person as the subject of analysis from others and to succinctly explain how the person relates to examining the research problem [e.g., why is one politician in a particular local election used to show an increase in voter turnout from any other candidate running in the election]. Note that these issues apply to a specific group of people used as a case study unit of analysis [e.g., a classroom of students].

If your subject of analysis is a place. In general, a case study that investigates a place suggests a subject of analysis that is unique or special in some way and that this uniqueness can be used to build new understanding or knowledge about the research problem. A case study of a place must not only describe its various attributes relevant to the research problem [e.g., physical, social, historical, cultural, economic, political], but you must state the method by which you determined that this place will illuminate new understandings about the research problem. It is also important to articulate why a particular place as the case for study is being used if similar places also exist [i.e., if you are studying patterns of homeless encampments of veterans in open spaces, explain why you are studying Echo Park in Los Angeles rather than Griffith Park?]. If applicable, describe what type of human activity involving this place makes it a good choice to study [e.g., prior research suggests Echo Park has more homeless veterans].

If your subject of analysis is a phenomenon. A phenomenon refers to a fact, occurrence, or circumstance that can be studied or observed but with the cause or explanation to be in question. In this sense, a phenomenon that forms your subject of analysis can encompass anything that can be observed or presumed to exist but is not fully understood. In the social and behavioral sciences, the case usually focuses on human interaction within a complex physical, social, economic, cultural, or political system. For example, the phenomenon could be the observation that many vehicles used by ISIS fighters are small trucks with English language advertisements on them. The research problem could be that ISIS fighters are difficult to combat because they are highly mobile. The research questions could be how and by what means are these vehicles used by ISIS being supplied to the militants and how might supply lines to these vehicles be cut off? How might knowing the suppliers of these trucks reveal larger networks of collaborators and financial support? A case study of a phenomenon most often encompasses an in-depth analysis of a cause and effect that is grounded in an interactive relationship between people and their environment in some way.

NOTE:   The choice of the case or set of cases to study cannot appear random. Evidence that supports the method by which you identified and chose your subject of analysis should clearly support investigation of the research problem and linked to key findings from your literature review. Be sure to cite any studies that helped you determine that the case you chose was appropriate for examining the problem.

IV.  Discussion

The main elements of your discussion section are generally the same as any research paper, but centered around interpreting and drawing conclusions about the key findings from your analysis of the case study. Note that a general social sciences research paper may contain a separate section to report findings. However, in a paper designed around a case study, it is common to combine a description of the results with the discussion about their implications. The objectives of your discussion section should include the following:

Reiterate the Research Problem/State the Major Findings Briefly reiterate the research problem you are investigating and explain why the subject of analysis around which you designed the case study were used. You should then describe the findings revealed from your study of the case using direct, declarative, and succinct proclamation of the study results. Highlight any findings that were unexpected or especially profound.

Explain the Meaning of the Findings and Why They are Important Systematically explain the meaning of your case study findings and why you believe they are important. Begin this part of the section by repeating what you consider to be your most important or surprising finding first, then systematically review each finding. Be sure to thoroughly extrapolate what your analysis of the case can tell the reader about situations or conditions beyond the actual case that was studied while, at the same time, being careful not to misconstrue or conflate a finding that undermines the external validity of your conclusions.

Relate the Findings to Similar Studies No study in the social sciences is so novel or possesses such a restricted focus that it has absolutely no relation to previously published research. The discussion section should relate your case study results to those found in other studies, particularly if questions raised from prior studies served as the motivation for choosing your subject of analysis. This is important because comparing and contrasting the findings of other studies helps support the overall importance of your results and it highlights how and in what ways your case study design and the subject of analysis differs from prior research about the topic.

Consider Alternative Explanations of the Findings Remember that the purpose of social science research is to discover and not to prove. When writing the discussion section, you should carefully consider all possible explanations revealed by the case study results, rather than just those that fit your hypothesis or prior assumptions and biases. Be alert to what the in-depth analysis of the case may reveal about the research problem, including offering a contrarian perspective to what scholars have stated in prior research if that is how the findings can be interpreted from your case.

Acknowledge the Study's Limitations You can state the study's limitations in the conclusion section of your paper but describing the limitations of your subject of analysis in the discussion section provides an opportunity to identify the limitations and explain why they are not significant. This part of the discussion section should also note any unanswered questions or issues your case study could not address. More detailed information about how to document any limitations to your research can be found here .

Suggest Areas for Further Research Although your case study may offer important insights about the research problem, there are likely additional questions related to the problem that remain unanswered or findings that unexpectedly revealed themselves as a result of your in-depth analysis of the case. Be sure that the recommendations for further research are linked to the research problem and that you explain why your recommendations are valid in other contexts and based on the original assumptions of your study.

V.  Conclusion

As with any research paper, you should summarize your conclusion in clear, simple language; emphasize how the findings from your case study differs from or supports prior research and why. Do not simply reiterate the discussion section. Provide a synthesis of key findings presented in the paper to show how these converge to address the research problem. If you haven't already done so in the discussion section, be sure to document the limitations of your case study and any need for further research.

The function of your paper's conclusion is to: 1) reiterate the main argument supported by the findings from your case study; 2) state clearly the context, background, and necessity of pursuing the research problem using a case study design in relation to an issue, controversy, or a gap found from reviewing the literature; and, 3) provide a place to persuasively and succinctly restate the significance of your research problem, given that the reader has now been presented with in-depth information about the topic.

Consider the following points to help ensure your conclusion is appropriate:

• If the argument or purpose of your paper is complex, you may need to summarize these points for your reader.
• If prior to your conclusion, you have not yet explained the significance of your findings or if you are proceeding inductively, use the conclusion of your paper to describe your main points and explain their significance.
• Move from a detailed to a general level of consideration of the case study's findings that returns the topic to the context provided by the introduction or within a new context that emerges from your case study findings.

Note that, depending on the discipline you are writing in or the preferences of your professor, the concluding paragraph may contain your final reflections on the evidence presented as it applies to practice or on the essay's central research problem. However, the nature of being introspective about the subject of analysis you have investigated will depend on whether you are explicitly asked to express your observations in this way.

Problems to Avoid

Overgeneralization One of the goals of a case study is to lay a foundation for understanding broader trends and issues applied to similar circumstances. However, be careful when drawing conclusions from your case study. They must be evidence-based and grounded in the results of the study; otherwise, it is merely speculation. Looking at a prior example, it would be incorrect to state that a factor in improving girls access to education in Azerbaijan and the policy implications this may have for improving access in other Muslim nations is due to girls access to social media if there is no documentary evidence from your case study to indicate this. There may be anecdotal evidence that retention rates were better for girls who were engaged with social media, but this observation would only point to the need for further research and would not be a definitive finding if this was not a part of your original research agenda.

Failure to Document Limitations No case is going to reveal all that needs to be understood about a research problem. Therefore, just as you have to clearly state the limitations of a general research study , you must describe the specific limitations inherent in the subject of analysis. For example, the case of studying how women conceptualize the need for water conservation in a village in Uganda could have limited application in other cultural contexts or in areas where fresh water from rivers or lakes is plentiful and, therefore, conservation is understood more in terms of managing access rather than preserving access to a scarce resource.

Failure to Extrapolate All Possible Implications Just as you don't want to over-generalize from your case study findings, you also have to be thorough in the consideration of all possible outcomes or recommendations derived from your findings. If you do not, your reader may question the validity of your analysis, particularly if you failed to document an obvious outcome from your case study research. For example, in the case of studying the accident at the railroad crossing to evaluate where and what types of warning signals should be located, you failed to take into consideration speed limit signage as well as warning signals. When designing your case study, be sure you have thoroughly addressed all aspects of the problem and do not leave gaps in your analysis that leave the reader questioning the results.

Case Studies. Writing@CSU. Colorado State University; Gerring, John. Case Study Research: Principles and Practices . New York: Cambridge University Press, 2007; Merriam, Sharan B. Qualitative Research and Case Study Applications in Education . Rev. ed. San Francisco, CA: Jossey-Bass, 1998; Miller, Lisa L. “The Use of Case Studies in Law and Social Science Research.” Annual Review of Law and Social Science 14 (2018): TBD; Mills, Albert J., Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Putney, LeAnn Grogan. "Case Study." In Encyclopedia of Research Design , Neil J. Salkind, editor. (Thousand Oaks, CA: SAGE Publications, 2010), pp. 116-120; Simons, Helen. Case Study Research in Practice . London: SAGE Publications, 2009;  Kratochwill,  Thomas R. and Joel R. Levin, editors. Single-Case Research Design and Analysis: New Development for Psychology and Education .  Hilldsale, NJ: Lawrence Erlbaum Associates, 1992; Swanborn, Peter G. Case Study Research: What, Why and How? London : SAGE, 2010; Yin, Robert K. Case Study Research: Design and Methods . 6th edition. Los Angeles, CA, SAGE Publications, 2014; Walo, Maree, Adrian Bull, and Helen Breen. “Achieving Economic Benefits at Local Events: A Case Study of a Local Sports Event.” Festival Management and Event Tourism 4 (1996): 95-106.

Writing Tip

At Least Five Misconceptions about Case Study Research

Social science case studies are often perceived as limited in their ability to create new knowledge because they are not randomly selected and findings cannot be generalized to larger populations. Flyvbjerg examines five misunderstandings about case study research and systematically "corrects" each one. To quote, these are:

Misunderstanding 1 :  General, theoretical [context-independent] knowledge is more valuable than concrete, practical [context-dependent] knowledge. Misunderstanding 2 :  One cannot generalize on the basis of an individual case; therefore, the case study cannot contribute to scientific development. Misunderstanding 3 :  The case study is most useful for generating hypotheses; that is, in the first stage of a total research process, whereas other methods are more suitable for hypotheses testing and theory building. Misunderstanding 4 :  The case study contains a bias toward verification, that is, a tendency to confirm the researcher’s preconceived notions. Misunderstanding 5 :  It is often difficult to summarize and develop general propositions and theories on the basis of specific case studies [p. 221].

While writing your paper, think introspectively about how you addressed these misconceptions because to do so can help you strengthen the validity and reliability of your research by clarifying issues of case selection, the testing and challenging of existing assumptions, the interpretation of key findings, and the summation of case outcomes. Think of a case study research paper as a complete, in-depth narrative about the specific properties and key characteristics of your subject of analysis applied to the research problem.

Flyvbjerg, Bent. “Five Misunderstandings About Case-Study Research.” Qualitative Inquiry 12 (April 2006): 219-245.

• << Previous: Writing a Case Analysis Paper
• Next: Writing a Field Report >>
• Last Updated: May 7, 2024 9:45 AM
• URL: https://libguides.usc.edu/writingguide/assignments

Conducting Case Study Research in Sociology

Steve Debenport / Getty Images

• Key Concepts
• Major Sociologists
• News & Issues
• Research, Samples, and Statistics
• Recommended Reading
• Archaeology

A case study is a research method that relies on a single case rather than a population or sample. When researchers focus on a single case, they can make detailed observations over a long period of time, something that cannot be done with large samples without costing a lot of money. Case studies are also useful in the early stages of research when the goal is to explore ideas, test, and perfect measurement instruments, and to prepare for a larger study. The case study research method is popular not just within ​the field of sociology, but also within the fields of anthropology, psychology, education, political science, clinical science, social work, and administrative science.

Overview of the Case Study Research Method

A case study is unique within the social sciences for its focus of study on a single entity, which can be a person, group or organization, event, action, or situation. It is also unique in that, as a focus of research, a case is chosen for specific reasons, rather than randomly , as is usually done when conducting empirical research. Often, when researchers use the case study method, they focus on a case that is exceptional in some way because it is possible to learn a lot about social relationships and social forces when studying those things that deviate from norms. In doing so, a researcher is often able, through their study, to test the validity of the social theory, or to create new theories using the grounded theory method .

The first case studies in the social sciences were likely conducted by Pierre Guillaume Frédéric Le Play, a 19th-century French sociologist and economist who studied family budgets. The method has been used in sociology, psychology, and anthropology since the early 20th century.

Within sociology, case studies are typically conducted with qualitative research methods . They are considered micro rather than macro in nature , and one cannot necessarily generalize the findings of a case study to other situations. However, this is not a limitation of the method, but a strength. Through a case study based on ethnographic observation and interviews, among other methods, sociologists can illuminate otherwise hard to see and understand social relations, structures, and processes. In doing so, the findings of case studies often stimulate further research.

Types and Forms of Case Studies

There are three primary types of case studies: key cases, outlier cases, and local knowledge cases.

• Key cases are those which are chosen because the researcher has ​a particular interest in it or the circumstances surrounding it.
• Outlier cases are those that are chosen because the case stands out from other events, organizations, or situations, for some reason, and social scientists recognize that we can learn a lot from those things that differ from the norm .
• Finally, a researcher may decide to conduct a local knowledge case study when they already have amassed a usable amount of information about a given topic, person, organization, or event, and so is well-poised to conduct a study of it.

Within these types, a case study may take four different forms: illustrative, exploratory, cumulative, and critical.

• Illustrative case studies are descriptive in nature and designed to shed light on a particular situation, set of circumstances, and the social relations and processes that are embedded in them. They are useful in bringing to light something about which most people are not aware of.
• Exploratory case studies are also often known as pilot studies . This type of case study is typically used when a researcher wants to identify research questions and methods of study for a large, complex study. They are useful for clarifying the research process, which can help a researcher make the best use of time and resources in the larger study that will follow it.
• Cumulative case studies are those in which a researcher pulls together already completed case studies on a particular topic. They are useful in helping researchers to make generalizations from studies that have something in common.
• Critical instance case studies are conducted when a researcher wants to understand what happened with a unique event and/or to challenge commonly held assumptions about it that may be faulty due to a lack of critical understanding.

Whatever type and form of case study you decide to conduct, it's important to first identify the purpose, goals, and approach for conducting methodologically sound research.

• An Overview of Qualitative Research Methods
• Understanding Secondary Data and How to Use It in Research
• Definition of Idiographic and Nomothetic
• Pilot Study in Research
• What Is Ethnography?
• How to Conduct a Sociology Research Interview
• The Sociology of the Internet and Digital Sociology
• What Is Participant Observation Research?
• Understanding Purposive Sampling
• The Different Types of Sampling Designs in Sociology
• Units of Analysis as Related to Sociology
• What Is Naturalistic Observation? Definition and Examples
• Social Surveys: Questionnaires, Interviews, and Telephone Polls
• Anthropology vs. Sociology: What's the Difference?
• Deductive Versus Inductive Reasoning
• How to Understand Interpretive Sociology

What is the Case Study Method?

Overview Dropdown up

Overview dropdown down, celebrating 100 years of the case method at hbs.

The 2021-2022 academic year marks the 100-year anniversary of the introduction of the case method at Harvard Business School. Today, the HBS case method is employed in the HBS MBA program, in Executive Education programs, and in dozens of other business schools around the world. As Dean Srikant Datar's says, the case method has withstood the test of time.

Case Discussion Preparation Details Expand All Collapse All

In self-reflection in self-reflection dropdown down, in a small group setting in a small group setting dropdown down, in the classroom in the classroom dropdown down, beyond the classroom beyond the classroom dropdown down, how the case method creates value dropdown up, how the case method creates value dropdown down, in self-reflection, in a small group setting, in the classroom, beyond the classroom.

How Cases Unfold In the Classroom

How cases unfold in the classroom dropdown up, how cases unfold in the classroom dropdown down, preparation guidelines expand all collapse all, read the professor's assignment or discussion questions read the professor's assignment or discussion questions dropdown down, read the first few paragraphs and then skim the case read the first few paragraphs and then skim the case dropdown down, reread the case, underline text, and make margin notes reread the case, underline text, and make margin notes dropdown down, note the key problems on a pad of paper and go through the case again note the key problems on a pad of paper and go through the case again dropdown down, how to prepare for case discussions dropdown up, how to prepare for case discussions dropdown down, read the professor's assignment or discussion questions, read the first few paragraphs and then skim the case, reread the case, underline text, and make margin notes, note the key problems on a pad of paper and go through the case again, case study best practices expand all collapse all, prepare prepare dropdown down, discuss discuss dropdown down, participate participate dropdown down, relate relate dropdown down, apply apply dropdown down, note note dropdown down, understand understand dropdown down, case study best practices dropdown up, case study best practices dropdown down, participate, what can i expect on the first day dropdown down.

Most programs begin with registration, followed by an opening session and a dinner. If your travel plans necessitate late arrival, please be sure to notify us so that alternate registration arrangements can be made for you. Please note the following about registration:

HBS campus programs – Registration takes place in the Chao Center.

India programs – Registration takes place outside the classroom.

Other off-campus programs – Registration takes place in the designated facility.

What happens in class if nobody talks? Dropdown down

Professors are here to push everyone to learn, but not to embarrass anyone. If the class is quiet, they'll often ask a participant with experience in the industry in which the case is set to speak first. This is done well in advance so that person can come to class prepared to share. Trust the process. The more open you are, the more willing you’ll be to engage, and the more alive the classroom will become.

Does everyone take part in "role-playing"? Dropdown down

Professors often encourage participants to take opposing sides and then debate the issues, often taking the perspective of the case protagonists or key decision makers in the case.

View Frequently Asked Questions

Subscribe to Our Emails

• Business Essentials
• Leadership & Management
• Credential of Leadership, Impact, and Management in Business (CLIMB)
• Entrepreneurship & Innovation
• Digital Transformation
• Finance & Accounting
• Business in Society
• For Organizations
• Support Portal
• Media Coverage
• Founding Donors
• Leadership Team

• Harvard Business School →
• HBS Online →
• Business Insights →

Business Insights

Harvard Business School Online's Business Insights Blog provides the career insights you need to achieve your goals and gain confidence in your business skills.

• Career Development
• Communication
• Decision-Making
• Earning Your MBA
• Negotiation
• News & Events
• Productivity
• Staff Spotlight
• Student Profiles
• Work-Life Balance
• AI Essentials for Business
• Alternative Investments
• Business Analytics
• Business Strategy
• Business and Climate Change
• Design Thinking and Innovation
• Digital Marketing Strategy
• Disruptive Strategy
• Economics for Managers
• Entrepreneurship Essentials
• Financial Accounting
• Global Business
• Launching Tech Ventures
• Leadership Principles
• Leadership, Ethics, and Corporate Accountability
• Leading with Finance
• Management Essentials
• Negotiation Mastery
• Organizational Leadership
• Power and Influence for Positive Impact
• Strategy Execution
• Sustainable Business Strategy
• Sustainable Investing
• Winning with Digital Platforms

5 Benefits of Learning Through the Case Study Method

• 28 Nov 2023

While several factors make HBS Online unique —including a global Community and real-world outcomes —active learning through the case study method rises to the top.

In a 2023 City Square Associates survey, 74 percent of HBS Online learners who also took a course from another provider said HBS Online’s case method and real-world examples were better by comparison.

Here’s a primer on the case method, five benefits you could gain, and how to experience it for yourself.

Access your free e-book today.

What Is the Harvard Business School Case Study Method?

The case study method , or case method , is a learning technique in which you’re presented with a real-world business challenge and asked how you’d solve it. After working through it yourself and with peers, you’re told how the scenario played out.

HBS pioneered the case method in 1922. Shortly before, in 1921, the first case was written.

“How do you go into an ambiguous situation and get to the bottom of it?” says HBS Professor Jan Rivkin, former senior associate dean and chair of HBS's master of business administration (MBA) program, in a video about the case method . “That skill—the skill of figuring out a course of inquiry to choose a course of action—that skill is as relevant today as it was in 1921.”

Originally developed for the in-person MBA classroom, HBS Online adapted the case method into an engaging, interactive online learning experience in 2014.

In HBS Online courses , you learn about each case from the business professional who experienced it. After reviewing their videos, you’re prompted to take their perspective and explain how you’d handle their situation.

You then get to read peers’ responses, “star” them, and comment to further the discussion. Afterward, you learn how the professional handled it and their key takeaways.

HBS Online’s adaptation of the case method incorporates the famed HBS “cold call,” in which you’re called on at random to make a decision without time to prepare.

“Learning came to life!” said Sheneka Balogun , chief administration officer and chief of staff at LeMoyne-Owen College, of her experience taking the Credential of Readiness (CORe) program . “The videos from the professors, the interactive cold calls where you were randomly selected to participate, and the case studies that enhanced and often captured the essence of objectives and learning goals were all embedded in each module. This made learning fun, engaging, and student-friendly.”

If you’re considering taking a course that leverages the case study method, here are five benefits you could experience.

5 Benefits of Learning Through Case Studies

1. take new perspectives.

The case method prompts you to consider a scenario from another person’s perspective. To work through the situation and come up with a solution, you must consider their circumstances, limitations, risk tolerance, stakeholders, resources, and potential consequences to assess how to respond.

Taking on new perspectives not only can help you navigate your own challenges but also others’. Putting yourself in someone else’s situation to understand their motivations and needs can go a long way when collaborating with stakeholders.

2. Hone Your Decision-Making Skills

Another skill you can build is the ability to make decisions effectively . The case study method forces you to use limited information to decide how to handle a problem—just like in the real world.

Throughout your career, you’ll need to make difficult decisions with incomplete or imperfect information—and sometimes, you won’t feel qualified to do so. Learning through the case method allows you to practice this skill in a low-stakes environment. When facing a real challenge, you’ll be better prepared to think quickly, collaborate with others, and present and defend your solution.

3. Become More Open-Minded

As you collaborate with peers on responses, it becomes clear that not everyone solves problems the same way. Exposing yourself to various approaches and perspectives can help you become a more open-minded professional.

When you’re part of a diverse group of learners from around the world, your experiences, cultures, and backgrounds contribute to a range of opinions on each case.

On the HBS Online course platform, you’re prompted to view and comment on others’ responses, and discussion is encouraged. This practice of considering others’ perspectives can make you more receptive in your career.

“You’d be surprised at how much you can learn from your peers,” said Ratnaditya Jonnalagadda , a software engineer who took CORe.

In addition to interacting with peers in the course platform, Jonnalagadda was part of the HBS Online Community , where he networked with other professionals and continued discussions sparked by course content.

“You get to understand your peers better, and students share examples of businesses implementing a concept from a module you just learned,” Jonnalagadda said. “It’s a very good way to cement the concepts in one's mind.”

4. Enhance Your Curiosity

One byproduct of taking on different perspectives is that it enables you to picture yourself in various roles, industries, and business functions.

“Each case offers an opportunity for students to see what resonates with them, what excites them, what bores them, which role they could imagine inhabiting in their careers,” says former HBS Dean Nitin Nohria in the Harvard Business Review . “Cases stimulate curiosity about the range of opportunities in the world and the many ways that students can make a difference as leaders.”

Through the case method, you can “try on” roles you may not have considered and feel more prepared to change or advance your career .

5. Build Your Self-Confidence

Finally, learning through the case study method can build your confidence. Each time you assume a business leader’s perspective, aim to solve a new challenge, and express and defend your opinions and decisions to peers, you prepare to do the same in your career.

According to a 2022 City Square Associates survey , 84 percent of HBS Online learners report feeling more confident making business decisions after taking a course.

“Self-confidence is difficult to teach or coach, but the case study method seems to instill it in people,” Nohria says in the Harvard Business Review . “There may well be other ways of learning these meta-skills, such as the repeated experience gained through practice or guidance from a gifted coach. However, under the direction of a masterful teacher, the case method can engage students and help them develop powerful meta-skills like no other form of teaching.”

How to Experience the Case Study Method

If the case method seems like a good fit for your learning style, experience it for yourself by taking an HBS Online course. Offerings span seven subject areas, including:

• Business essentials
• Leadership and management
• Entrepreneurship and innovation
• Finance and accounting
• Business in society

No matter which course or credential program you choose, you’ll examine case studies from real business professionals, work through their challenges alongside peers, and gain valuable insights to apply to your career.

Are you interested in discovering how HBS Online can help advance your career? Explore our course catalog and download our free guide —complete with interactive workbook sections—to determine if online learning is right for you and which course to take.

About the Author

• Bipolar Disorder
• Therapy Center
• When To See a Therapist
• Types of Therapy
• Best Online Therapy
• Best Couples Therapy
• Best Family Therapy
• Managing Stress
• Sleep and Dreaming
• Understanding Emotions
• Self-Improvement
• Healthy Relationships
• Student Resources
• Personality Types
• Guided Meditations
• Verywell Mind Insights
• 2024 Verywell Mind 25
• Mental Health in the Classroom
• Editorial Process
• Meet Our Review Board
• Crisis Support

What Is a Case Study?

Weighing the pros and cons of this method of research

Kendra Cherry, MS, is a psychosocial rehabilitation specialist, psychology educator, and author of the "Everything Psychology Book."

Cara Lustik is a fact-checker and copywriter.

Verywell / Colleen Tighe

• Pros and Cons

What Types of Case Studies Are Out There?

Where do you find data for a case study, how do i write a psychology case study.

A case study is an in-depth study of one person, group, or event. In a case study, nearly every aspect of the subject's life and history is analyzed to seek patterns and causes of behavior. Case studies can be used in many different fields, including psychology, medicine, education, anthropology, political science, and social work.

The point of a case study is to learn as much as possible about an individual or group so that the information can be generalized to many others. Unfortunately, case studies tend to be highly subjective, and it is sometimes difficult to generalize results to a larger population.

While case studies focus on a single individual or group, they follow a format similar to other types of psychology writing. If you are writing a case study, we got you—here are some rules of APA format to reference.  

At a Glance

A case study, or an in-depth study of a person, group, or event, can be a useful research tool when used wisely. In many cases, case studies are best used in situations where it would be difficult or impossible for you to conduct an experiment. They are helpful for looking at unique situations and allow researchers to gather a lot of˜ information about a specific individual or group of people. However, it's important to be cautious of any bias we draw from them as they are highly subjective.

What Are the Benefits and Limitations of Case Studies?

A case study can have its strengths and weaknesses. Researchers must consider these pros and cons before deciding if this type of study is appropriate for their needs.

One of the greatest advantages of a case study is that it allows researchers to investigate things that are often difficult or impossible to replicate in a lab. Some other benefits of a case study:

• Allows researchers to capture information on the 'how,' 'what,' and 'why,' of something that's implemented
• Gives researchers the chance to collect information on why one strategy might be chosen over another
• Permits researchers to develop hypotheses that can be explored in experimental research

On the other hand, a case study can have some drawbacks:

• It cannot necessarily be generalized to the larger population
• Cannot demonstrate cause and effect
• It may not be scientifically rigorous
• It can lead to bias

Researchers may choose to perform a case study if they want to explore a unique or recently discovered phenomenon. Through their insights, researchers develop additional ideas and study questions that might be explored in future studies.

It's important to remember that the insights from case studies cannot be used to determine cause-and-effect relationships between variables. However, case studies may be used to develop hypotheses that can then be addressed in experimental research.

Case Study Examples

There have been a number of notable case studies in the history of psychology. Much of  Freud's work and theories were developed through individual case studies. Some great examples of case studies in psychology include:

• Anna O : Anna O. was a pseudonym of a woman named Bertha Pappenheim, a patient of a physician named Josef Breuer. While she was never a patient of Freud's, Freud and Breuer discussed her case extensively. The woman was experiencing symptoms of a condition that was then known as hysteria and found that talking about her problems helped relieve her symptoms. Her case played an important part in the development of talk therapy as an approach to mental health treatment.
• Phineas Gage : Phineas Gage was a railroad employee who experienced a terrible accident in which an explosion sent a metal rod through his skull, damaging important portions of his brain. Gage recovered from his accident but was left with serious changes in both personality and behavior.
• Genie : Genie was a young girl subjected to horrific abuse and isolation. The case study of Genie allowed researchers to study whether language learning was possible, even after missing critical periods for language development. Her case also served as an example of how scientific research may interfere with treatment and lead to further abuse of vulnerable individuals.

Such cases demonstrate how case research can be used to study things that researchers could not replicate in experimental settings. In Genie's case, her horrific abuse denied her the opportunity to learn a language at critical points in her development.

This is clearly not something researchers could ethically replicate, but conducting a case study on Genie allowed researchers to study phenomena that are otherwise impossible to reproduce.

There are a few different types of case studies that psychologists and other researchers might use:

• Collective case studies : These involve studying a group of individuals. Researchers might study a group of people in a certain setting or look at an entire community. For example, psychologists might explore how access to resources in a community has affected the collective mental well-being of those who live there.
• Descriptive case studies : These involve starting with a descriptive theory. The subjects are then observed, and the information gathered is compared to the pre-existing theory.
• Explanatory case studies : These   are often used to do causal investigations. In other words, researchers are interested in looking at factors that may have caused certain things to occur.
• Exploratory case studies : These are sometimes used as a prelude to further, more in-depth research. This allows researchers to gather more information before developing their research questions and hypotheses .
• Instrumental case studies : These occur when the individual or group allows researchers to understand more than what is initially obvious to observers.
• Intrinsic case studies : This type of case study is when the researcher has a personal interest in the case. Jean Piaget's observations of his own children are good examples of how an intrinsic case study can contribute to the development of a psychological theory.

The three main case study types often used are intrinsic, instrumental, and collective. Intrinsic case studies are useful for learning about unique cases. Instrumental case studies help look at an individual to learn more about a broader issue. A collective case study can be useful for looking at several cases simultaneously.

The type of case study that psychology researchers use depends on the unique characteristics of the situation and the case itself.

There are a number of different sources and methods that researchers can use to gather information about an individual or group. Six major sources that have been identified by researchers are:

• Archival records : Census records, survey records, and name lists are examples of archival records.
• Direct observation : This strategy involves observing the subject, often in a natural setting . While an individual observer is sometimes used, it is more common to utilize a group of observers.
• Documents : Letters, newspaper articles, administrative records, etc., are the types of documents often used as sources.
• Interviews : Interviews are one of the most important methods for gathering information in case studies. An interview can involve structured survey questions or more open-ended questions.
• Participant observation : When the researcher serves as a participant in events and observes the actions and outcomes, it is called participant observation.
• Physical artifacts : Tools, objects, instruments, and other artifacts are often observed during a direct observation of the subject.

If you have been directed to write a case study for a psychology course, be sure to check with your instructor for any specific guidelines you need to follow. If you are writing your case study for a professional publication, check with the publisher for their specific guidelines for submitting a case study.

Here is a general outline of what should be included in a case study.

Section 1: A Case History

This section will have the following structure and content:

Background information : The first section of your paper will present your client's background. Include factors such as age, gender, work, health status, family mental health history, family and social relationships, drug and alcohol history, life difficulties, goals, and coping skills and weaknesses.

Description of the presenting problem : In the next section of your case study, you will describe the problem or symptoms that the client presented with.

Describe any physical, emotional, or sensory symptoms reported by the client. Thoughts, feelings, and perceptions related to the symptoms should also be noted. Any screening or diagnostic assessments that are used should also be described in detail and all scores reported.

Your diagnosis : Provide your diagnosis and give the appropriate Diagnostic and Statistical Manual code. Explain how you reached your diagnosis, how the client's symptoms fit the diagnostic criteria for the disorder(s), or any possible difficulties in reaching a diagnosis.

Section 2: Treatment Plan

This portion of the paper will address the chosen treatment for the condition. This might also include the theoretical basis for the chosen treatment or any other evidence that might exist to support why this approach was chosen.

• Cognitive behavioral approach : Explain how a cognitive behavioral therapist would approach treatment. Offer background information on cognitive behavioral therapy and describe the treatment sessions, client response, and outcome of this type of treatment. Make note of any difficulties or successes encountered by your client during treatment.
• Humanistic approach : Describe a humanistic approach that could be used to treat your client, such as client-centered therapy . Provide information on the type of treatment you chose, the client's reaction to the treatment, and the end result of this approach. Explain why the treatment was successful or unsuccessful.
• Psychoanalytic approach : Describe how a psychoanalytic therapist would view the client's problem. Provide some background on the psychoanalytic approach and cite relevant references. Explain how psychoanalytic therapy would be used to treat the client, how the client would respond to therapy, and the effectiveness of this treatment approach.
• Pharmacological approach : If treatment primarily involves the use of medications, explain which medications were used and why. Provide background on the effectiveness of these medications and how monotherapy may compare with an approach that combines medications with therapy or other treatments.

This section of a case study should also include information about the treatment goals, process, and outcomes.

When you are writing a case study, you should also include a section where you discuss the case study itself, including the strengths and limitiations of the study. You should note how the findings of your case study might support previous research. 

In your discussion section, you should also describe some of the implications of your case study. What ideas or findings might require further exploration? How might researchers go about exploring some of these questions in additional studies?

Need More Tips?

Here are a few additional pointers to keep in mind when formatting your case study:

• Never refer to the subject of your case study as "the client." Instead, use their name or a pseudonym.
• Read examples of case studies to gain an idea about the style and format.
• Remember to use APA format when citing references .

Crowe S, Cresswell K, Robertson A, Huby G, Avery A, Sheikh A. The case study approach .  BMC Med Res Methodol . 2011;11:100.

Crowe S, Cresswell K, Robertson A, Huby G, Avery A, Sheikh A. The case study approach . BMC Med Res Methodol . 2011 Jun 27;11:100. doi:10.1186/1471-2288-11-100

Gagnon, Yves-Chantal.  The Case Study as Research Method: A Practical Handbook . Canada, Chicago Review Press Incorporated DBA Independent Pub Group, 2010.

Yin, Robert K. Case Study Research and Applications: Design and Methods . United States, SAGE Publications, 2017.

By Kendra Cherry, MSEd Kendra Cherry, MS, is a psychosocial rehabilitation specialist, psychology educator, and author of the "Everything Psychology Book."

• Harvard Business School →
• Christensen Center →

Teaching by the Case Method

• Preparing to Teach
• Leading in the Classroom
• Providing Assessment & Feedback
• Sample Class

Case Method in Practice

Chris Christensen described case method teaching as "the art of managing uncertainty"—a process in which the instructor serves as "planner, host, moderator, devil's advocate, fellow-student, and judge," all in search of solutions to real-world problems and challenges.

Unlike lectures, case method classes unfold without a detailed script. Successful instructors simultaneously manage content and process, and they must prepare rigorously for both. Case method teachers learn to balance planning and spontaneity. In practice, they pursue opportunities and "teachable moments" that emerge throughout the discussion, and deftly guide students toward discovery and learning on multiple levels. The principles and techniques are developed, Christensen says, "through collaboration and cooperation with friends and colleagues, and through self-observation and reflection."

This section of the Christensen Center website explores the Case Method in Practice along the following dimensions:

• Providing Assessment and Feedback

Each subsection provides perspectives and guidance through a written overview, supplemented by video commentary from experienced case method instructors. Where relevant, links are included to downloadable documents produced by the Christensen Center or Harvard Business School Publishing. References for further reading are provided as well.

An additional subsection, entitled Resources, appears at the end. It combines references from throughout the Case Method in Practice section with additional information on published materials and websites that may be of interest to prospective, new, and experienced case method instructors.

Note: We would like to thank Harvard Business School Publishing for permission to incorporate the video clips that appear in the Case Method in Practice section of our website. The clips are drawn from video excerpts included in Participant-Centered Learning and the Case Method: A DVD Case Teaching Tool (HBSP, 2003).

Christensen Center Tip Sheets

• Characteristics of Effective Case Method Teaching
• Elements of Effective Class Preparation
• Guidelines for Effective Observation of Case Instructors
• In-Class Assessment of Discussion-Based Teaching
• Questions for Class Discussions
• Teaching Quantitative Material
• Strategies and Tactics for Sensitive Topics

Curriculum Innovation

The case method has evolved so students may act as decision-makers in new engaging formats:

Game Simulations

Multimedia cases, ideo: human-centered service design.

What is the case method?

The case method is a teaching methodology based on the study and discussion of real business cases intended to help managers like you improve your decision-making skills. The method, established in 1921 by Harvard Business School, ultimately teaches you the art of managing uncertainty.

The case method is the art of managing uncertainty. Chris Christensen, Harvard Business School Professor

And what is the most important thing for you to do as a manager in uncertain situations? Make decisions . After all, you’re responsible for taking the initiative on finding the proper solution to a specific problem.

There are two types of problems you’ll face while making business decisions. There are those that can be solved objectively through a set process or equation and that require a single correct response. Then there are others that can be solved in a variety of ways. It’s the second type of problem that usually falls to you, the executive, to fix.

Can you learn this type of decision-making capability? Yes. In fact, that is precisely the goal of the case method: learning to respond to what are called “non-operational” problems in the business world. This methodology places you and your classmates in the role of manager when identifying the problems discussed in each case and seeking answers to problems. Crucially, it also prizes dynamic interaction between a diverse group of participants

4 reasons why the case method is the best learning methodology

1. real world experience.

The case method is the methodology that best reflects the realities you face as a manager. It helps you identify symptoms and grapple with problems that appear without obvious solutions. The goal is that the judicious decisions you make in a classroom setting will enable you to make them in the professional world.

2. Calibrated conversation

The case method allows you to learn through the discussion of previously prepared cases. Many of these cases will have been prepared by your professors and are based on their own business experiences.

3. An expansive view

The challenges posed by the cases presented to you will not have a single solution. It’s precisely that range of possible solutions, which you’ll discuss in-depth with your classmates, that makes the method such a valuable experience. With the case method, you’ll constantly learn from the insights and opinions of your fellow participants and the professor.

4. Cross-functional preparation

The case method will refine your management knowledge in ways that can be applied to a wide range of departments in your company, including finances, operations and human resources. At the same time, it will offer you a global vision of the repercussions your decisions may have on the organization.

Learn how the IESE case method works .

If you’re a prospective MBA student interested in learning more about the case method, consider attending an IESE Open Day for an in-person experience of the methodology. IESE’s Executive Education programs also offer you training tailored to whichever step along your career path you find yourself on, wherever you find yourself and whatever the challenges ahead.

Related Posts

• Search Menu
• Advance articles
• Author Guidelines
• Submission Site
• Open Access
• Why Submit?
• About Applied Linguistics
• Editorial Board
• Advertising and Corporate Services
• Journals Career Network
• Self-Archiving Policy
• Dispatch Dates
• Terms and Conditions
• Journals on Oxford Academic
• Books on Oxford Academic

Article Contents

Introduction, literature review, methodology, analysis and results, audience design for chatbots: a way forward, acknowledgments, making the case for audience design in conversational ai: users’ pragmatic strategies and rapport expectations in interaction with a task-oriented chatbot.

• Article contents
• Figures & tables
• Supplementary Data

Doris Dippold, Making the Case for Audience Design in Conversational AI: Users’ Pragmatic Strategies and Rapport Expectations in Interaction with a Task-Oriented Chatbot, Applied Linguistics , 2024;, amae033, https://doi.org/10.1093/applin/amae033

• Permissions Icon Permissions

With chatbots becoming more and more prevalent in commercial and service contexts, they need to be designed to provide equitable access to services for all user groups. This paper argues that insights into users’ pragmatic strategies and rapport expectations can inform the audience design of chatbots and ensure that all users can equally benefit from the services they facilitate. The argument is underpinned by the analysis of simulated user interactions with a chatbot facilitating health appointment bookings, users’ introspective comments on their interactions, and users’ qualitative survey comments. The study shows that users’ pragmatic strategies show considerable variation. It also shows the negative impact of user experiences when the chatbot’s language and interaction patterns do not align with users’ rapport expectations. In closing, the paper uses these findings to define audience design for chatbots and discuss how audience design can be realized and supported by research.

Chatbots are becoming ever more common in daily life, taking over customer service functions, offering advice, and facilitating access to public services, for example, through appointment booking. In this paper, I aim to show that improved audience design—the adaptive design of bot dialogue in line with users’ pragmatic practices and expectations—will better align services with principles of equality (giving everyone equal opportunities), diversity (valuing difference), and inclusion (ensuring access to services).

The cornerstone of my approach is an investigation of chatbot users’ pragmatic strategies. Whilst the analytical focus is primarily on particular politeness strategies ( Brown and Levinson 1987 ), the paper will also look at users’ deployment of other pragmatic strategies. These include greetings and partings which serve as access rituals ( Goffman 1971 : 79) and as face-saving strategies ( Laver 1981 ), self-disclosure ( Haugh and Carbaugh 2015 ), discourse markers ( Fraser 1999 ), expressions of thanks as an indication of alignment ( Aston 1995 ), and the use of pronouns and names as forms of address in interaction with an appointment booking chatbot. These are triangulated with user comments, made in surveys and interviews, on how these pragmatic strategies connect to their expectations for rapport ( Spencer-Oatey 2008 ). In chatbot research, investigations of users’ pragmatic strategies are still relatively scarce, in particular those using ethnographic and qualitative approaches (see literature review). This study investigates these strategies in a semi-naturalistic setting and thus addresses a gap in human–machine interaction research, underpinning a discussion on how cultural sensitivity within chatbot interactions can be enhanced in the future.

To introduce my argument regarding the need for audience design, a look at two frequently cited studies of language use in interethnic and intercultural contexts. We start with Gumperz’ (1982) case study relating to events at Heathrow Airport in the late 1970s. Pakistani and Indian staff there were hired to serve food at a staff canteen but were perceived as rude and uncooperative by British supervisors and customers. After recording service interactions in the cafeteria, Gumperz found that the Indian and Pakistani staff tended to use falling intonation when making service-related requests. Interpreting these intonation patterns against their background expectations of phonetic patterns, British speakers of English interpreted these requests as unnecessary statements rather than offers and judged the Indian and Pakistani staff to be rude.

More than 20 years later, Spencer-Oatey and Xing (2003) and Spencer-Oatey (2005) investigated participants’ pragmatic strategies and rapport expectations in a Chinese-British business meeting. Drawing on transcriptions of video recordings, retrospective comments by participants and researcher observations, the authors showed that rapport between participants is centred around and can be threatened by individuals’ perceptions of different aspects of language and discourse, for example, stylistic choices, turn management, topic choice, sequencing of information, and so on, as well as differences in their assessment of contextual factors.

These classic case studies have one central aspect in common: they all emphasize how specific language strategies, dialogue patterns, and conversational expectations drive individuals’ perceptions of other social actors. In this paper, I will take these ideas forward to propose that artificial social actors such as chatbots need to be subjected to audience design to mimic the way that human social actors adapt to different audiences, no matter whether these differences are defined by users’ linguistic or cultural backgrounds or other factors, such as age.

The paper starts with a literature review in which I will introduce the notion of audience design, review previous research on users’ expectations of chatbot dialogue and describe the main theoretical approaches framing this study, politeness theory ( Brown and Levinson 1987 ), and rapport management ( Spencer-Oatey 2008 ). In the methodology section, I will discuss the triangulated research design consisting of an analysis of user interactions with a chatbot, surveys, and user interviews, participant recruitment and the analytical approach. I present the results in the form of the case studies of two users’ interactions with the chatbot, followed by a discussion of users’ pragmatic strategies and rapport expectations against the backdrop of the three rapport management dimensions of face, sociality rights, and interactional goals. I close with a definition of audience design for chatbots, its importance and a research agenda for audience design in human–machine interaction.

Introducing audience design

The concept of audience design derives from Bell (1984 , 2001 ). The key take-home-message is that ‘speakers design their style primarily for and in response to their audience’ (143). Bell (1984) roots the concept explicitly in sociolinguistic theory, defining the factors influencing language variation in the design of speech for different audiences as both linguistic (e.g. phonology, syntax, etc.) and extralinguistic, including interspeaker (class, age, etc.) and intraspeaker (addressee, topic, etc.) variation. In his ‘reworked’ audience design concept, Bell (2001) further stresses that style shift also includes encoding the speaker’s own identity in relation to their audience. Audience design shows reflections of Hymes’ (1974)   ‘SPEAKING’ mnemonic which purports that linguistic competence requires an acknowledgement of context in speaking. It also integrates Gumperz’s (1982) notion of contextualization cues that describes how listeners interpret verbal and nonverbal features in line with their expectations of social interaction.

Previous research on users’ expectations of chatbot dialogue

The majority of the research on people’s perceptions of interactions with bots and other forms of conversational AI so far uses experimental methods rather than data gathered ‘in the wild’. Their insights underline not only the importance of building conversational agents that have the ability to build and sustain rapport with their users but also the importance of aligning the language strategies of the bot with the expectations of their users. For example, Srinivasan (2016) systematically manipulated the politeness levels of requests (e.g. positive politeness, negative politeness, etc.) used by chatbots in interaction with users. They found that the use of positive politeness was more likely to entice people to help the robots complete tasks, such as to open a door. Salem et al. (2014) investigated the effects of politeness and culture on robot acceptance and anthropomorphization. They found that the more polite robot was perceived to exhibit greater warmth than the control robot. Moreover, they also found that native speakers of English and of Arabic evaluated the robot differently, suggesting that differences in language and sociocultural background between users may be guiding users’ perceptions. Finally, the importance of conversational agents building rapport with users was shown in a study by Bickmore and Pickard (2005) who found that an artificial agent supporting users with a new fitness regime attracted more respect, was liked more, and generated more trust than a non-relational agent and made users more likely to want to continue working with the agent.

The importance of alignment of conversational AI systems with user preferences and expectations has been confirmed in research on text-based chatbots and voice–user interfaces. Cowan et al. (2016) operationalized dialectal variation as a factor for users’ perceptions of the credibility of a navigation system. They found that a navigation system speaking with an Irish voice was considered more credible by its Irish users, no matter how accurate it was. Li and Mao (2015) confirmed the importance of user alignment with their study on a virtual health advisory system. They showed that, when the system’s communication style aligned with a user’s style, it was perceived to be more enjoyable, credible, informative, and transparent. Moreover, Følstad et al. (2020), in a questionnaire-based study on user experiences with chatbots, found that user experience, user needs, and user expectations varied with age. Younger users expected more elements that allowed for the engagement with the bot to be evocative or stimulating, whereas older users preferred elements that were oriented towards the task and general productivity. Van der Goot (2021) described customers’ ‘communication journeys’ with chatbots through the help of interviews with respondents of different genders, ages, and educational levels. They found that customer journeys were strongly influenced by customers’ prior expectations of the interaction, their experiences during the conversations, the effort required, and the extent to which the bot appeared to be human-like. Finally, the study also revealed that there were differences in users’ expectations of language style, for example, of the use of formal vs. informal style.

Another tranche of studies describes how users interact with conversational AI by drawing on the micro-analytical techniques provided by conversation analysis. For example, Hill et al. (2015) investigated differences between human–human interaction via instant messenger and human–chatbot interaction. They found that users’ pragmatic strategies were linked to their perceptions of how human-like their conversational partner was. When interacting with chatbots, users used more profanity and less rich vocabulary than when they were interacting with humans via instant messenger. Braunger et al ’.s (2017) study on user interactions with an in-car spoken dialogue system revealed that speakers were influenced by their beliefs about the system, leading them to adapt to the system, for example, through the use of short concise phrases. Finally, Pelikan (2015) and Pelikan and Broth (2016) investigated how humans adapt to embodied robots, revealing that users adapted their turn design and turn-taking strategies to be in line with their expectations of the conversations.

So far, there is a scarcity of studies that explicitly investigate users’ pragmatic strategies in interaction with chatbots. In one study which is based on the same dataset than the one for this paper ( Dippold 2023 ). I revealed that some users’ strategies that are more akin to human–human interaction are less likely to be successful than those that accommodate the chatbot’s strategies. The only cross-cultural study of users’ pragmatic strategies in interaction with chatbots known to me is Timpe-Laughlin and Dombi’s (2020) comparison of L2 Hungarian and L1 Japanese learners’ English requests to an automated agent. The study not only showed distinct differences in both groups’ strategies to learners’ requests elicited in other interlanguage studies of requests, such as more direct strategies and more internal rather than external modifiers. In addition, it also showed differences in the realization of requests between the two groups. This study is significant as it is perhaps the first attempt to systematically describe the request strategies of different linguistic and cultural groups, insights from which are important to inform audience design through a window into users’ practices.

In summary, existing studies suggest that users have more positive perceptions of conversational systems that are perceived to be creating rapport with users and whose spoken or written output strategies align with user characteristics and expectations. Studies also found that users adapt their pragmatic strategies to their perceptions and expectations of the conversational system. This suggests that a more user-centred design of chatbot language and interaction patterns needs to consider users’ expectations and preferences as well as their pragmatic strategies in interaction with chatbots. This study thus seeks to address this research gap by combining an investigation into users’ rapport expectations—as supported by the chatbot’s dialogue patterns—with an exploration of users’ own pragmatic strategies.

Research questions

This paper supports the research agenda of human–machine interaction by investigating two central questions:

What pragmatic strategies do people use when interacting with chatbots?

In what way do users’ rapport expectations influence their enjoyment of interacting with the chatbot?

The insights from both of these research questions will allow for ethnographically grounded and qualitative insights into users’ authentic pragmatic strategies and rapport expectations and the relationship between these strategies and expectations. Given the experimental focus of most prior studies and a lack of investigation into pragmatic strategies in human–machine contexts, this study thus addresses an important research need. This empirically informed discussion on these issues will later feed into a more extensive discussion of the need for audience design for AI and how audience design can be practically realized and supported through research.

Theoretical frameworks

This paper will answer these questions by drawing on two main theoretical approaches. For the analysis of users’ pragmatic strategies (research question 1), politeness theory ( Brown and Levinson 1987 ) is the guiding theoretical framework. This seminal work on politeness distinguishes positive politeness strategies (addressing human needs for connection and approval), negative politeness strategies (addressing human needs for distance and avoiding imposition), off-record politeness (indirect speech acts), and on-record strategies which are delivered without any mitigation. In addition, the consideration of users’ pragmatic strategies also involves other indicators, such as greetings and partings, self-disclosure, discourse markers, expressions of thanks and forms of address.

In addition, Spencer-Oatey’s (2008) rapport management framework provides the backdrop to the analysis for research question 2. The framework describes rapport as ‘people’s subjective perceptions of (dis)harmony, smoothness-turbulence and warmth-antagonism in interpersonal relations’ ( Spencer-Oatey and Franklin 2009 : 102) and as managed across three dimensions ( Spencer-Oatey 2008 ). The first one of these is face (the need to have personal qualities and social roles upheld) and sociality rights and obligations, consisting of equity rights (rights to personal consideration from others) and association rights (rights to an association with others that is in keeping with the relationship we have with them). The third dimension is that of interactional goals , distinguishing whether speakers focus primarily on completing the task (transactional goals) or on establishing a relationship (relational goals).

Data collection instruments

The data were collected as part of a research project conducted conjointly with start-up company spryt.com. SPRYT have developed an intelligent patient scheduling system that allows patients—currently only using English—to schedule medical appointments via text-based interactions on WhatsApp. Patients interact with a digital receptionist—the chatbot—called ‘Asa’ to schedule appointments, amend or cancel appointments, or respond to a medical screening questionnaire.

As a result of the main author’s post on a UK National Health System (NHS) AI discussion board, SPRYT asked for their support in supporting Asa’s development through her academic expertise. This research project represented the first time the scheduling system was tested with users in a simulated setting and the methodology was developed in collaboration with SPRYT. After the project, the main author gave feedback to SPRYT on aspects of Asa’s dialogue design. The author received no monetary compensation for this work but has benefited from producing publications and evidence of research impact.

Data were gathered through three research instruments:

User experience interviews (see supplementary data A ): Ten interviews were planned in collaboration with an experienced UX researcher. Interviews initially centred on users’ routines and everyday lives and then their general booking experiences for booking both health-related and other appointments. After this phase of the interview, the researcher then triggered Asa to contact the user via WhatsApp on their phone. Users were given a range of tasks to complete with Asa—for example, scheduling an appointment, cancelling an appointment, answering the patient invitation questionnaire. With every bot turn, they were asked what they liked about Asa’s response, what they disliked, what they thought they should be doing next, and what they would actually do next.

Survey (see supplementary data B ): After the user experience interviews, spryt.com made some changes to the wording of some turns and to the interaction structure of Asa, based on the researchers’ recommendations. Further data were then gathered through a survey which again asked for users’ experiences of booking, scheduling, and cancelling appointments and responding to the medical screening questionnaire. The survey included a mixture of closed and open-ended questions. Participants completed the survey soon after interacting with Asa. 32 participants were recruited for this stage.

User–bot interactions: Across the interview and the survey stage, 36 users interacted with Asa and made their interactions available for analysis. In the case of the interactions gathered as part of the interview stage, it is possible to directly crossmatch these to participant interviews that allows for insights into specific moments in the interactions. As the surveys were anonymous, answers within the survey and the interactions of respondents with Asa cannot be cross-matched.

At the time when data were collected, Asa generated templated responses from a pre-programmed response pool which were designed by the company CEO and the wider technical team. For the first 10 of the user interactions with Asa (interview stage), the system was not set up to greet users by their own name, which resulted in a greeting of ‘Hi, Test’. In the survey stage, Asa greeted users by their own names, which have been pseudonymized to maintain anonymity.

In the transcripts presented in this paper, see example 3 below Asa’s turns are represented in italics, whereas users’ responses are represented in regular typeface. Words framed by an asterisk * on each side (see, e.g. 3, 1, 4–5) would have appeared as bold on the users’ mobile phone. The purpose of this was to indicate users that using these words in a response would start a specific conversational path. However, this was not made explicit to users. Statements introduced by a dot • (e.g. lines 7–10) would have appeared as a line-separated bullet point to users.

1 What do I need to do before the appointment?

2 You can find us at, Stag Hill, University Campus, Guildford, GU2 7XH, UK

3 Can I eat before an mri

4 Are you trying to say? *general information* *schedule* appointment *prepare* for

5 appointment *None* of these

6 Prepare for appointment

7 The scan will be around 30 min • *Unless we let you know otherwise*, you can eat and drink

8 as normal and take any prescribed medication • You’re welcome to bring a friend or a relative

9 with you • The radiography team with explain the process once you arrive Do you have any

10 other questions or concerns about what to expect on the day?

11 Will it hurt

12 Sorry, I didn’t understand that. Can you say that in a different way?

13 Can I cancel the appointment

14 Okay,. Please let me know the number of the appointment you would like to cancel: 1.

15 Screening on Tue 22 Mar ‘22 at 16:00

Participant recruitment and demographics

Participants were recruited through the researchers’ social media channels as well as the university’s experimental platform. In the interviews, the majority of participants were undergraduate and postgraduate university students, in addition to two professionals who took part in the research due to professional interest in chatbot development. In the survey, the majority of participants (45 per cent) were between 18 and 24 years old and more than 70 per cent described their ethnicity as ‘White’. Due to the relatively low participant number, I will use the data only to derive theoretical insights rather than attempting to provide verifiable insights into different user group’s pragmatic strategies and rapport expectations.

Participants in both stages of the project were provided with an information sheet. Interview participants signed a written consent form, and participants in the survey stage indicated their consent electronically before starting the survey.

Data analysis

User–bot interactions..

User–bot interactions were downloaded from SPRYT’s dashboard for the trial clinic that was specifically created for the purpose of this project. The transcript files were uploaded into the qualitative analysis programme NVivo. NVivo was then used to code the data with respect to users’ pragmatic strategies, including

directly addressing Asa, for example, Hi, 2 nd   person pronouns (‘you’)

discourse markers (e.g. actually , sorry to be a pain)

greetings and partings (e.g. Goodbye)

self-disclosure (e.g. the user telling Asa their name)

expressions of thanks (e.g. Okay, thank you )

expressions of positive politeness, negative politeness, off-record and on-record politeness strategies in users’ requests for information, requests for scheduling, cancellation or rescheduling and their confirmations of attendance or compliance.

The paper will discuss to what extent these pragmatic strategies betray users’ orientations to Asa to be relationship-focussed and anthropomorphic—that is, users orient to the agent as humanlike—or task-focused, orientating to Asa as a machine ( Waytz et al. 2010 ).

Interviews and surveys.

The interviews were recorded on MS Teams. The automatically generated transcripts were downloaded and edited into a word-level transcript by a research assistant, after which they were uploaded onto Nvivo. Users’ responses to the open questions in the survey were also extracted and uploaded onto Nvivo.

The qualitative data from both the interviews and the survey were analysed using reflexive thematic analysis ( Braun and Clarke 2019 ) describes themes as ‘creative and interpretive stories about the data, produced at the intersection of the researcher’s theoretical assumptions, their analytic resources and skill, and the data themselves’ (594). Whilst the initial data approach was ‘bottom-up’, inductive, and data driven, I soon realized that one of the main stories users were telling was about their needs when booking appointments more generally, and their experiences and needs when booking through Asa (e.g. efficiency, confidentiality, being listened to). Consequently, I started using a deductive approach, drawing on a combination of semantic coding—using what a respondent has said or written—and latent coding—interpreting underlying meaning and ideas ( Byrne 2022 )—to code the entire dataset against this theme and these sub-themes. Given the analytical focus on issues of rapport, instances in which participants talked about ‘incidents’ within the interaction with Asa which has a negative effect (e.g. feeling annoyed, insulted, etc.) or a positive effect (feeling happy, proud, a sense of achievement) on them (see Spencer-Oatey 2002 ), were particularly helpful in this phase of latent coding.

In the subsequent section, I will draw on the analysis of the users’ pragmatic strategies in interaction with Asa as well as the analysis of interview and survey data in relation to the rapport management framework. The presentation of the results starts with two case studies. Subsequently, I will discuss users’ comments from the surveys and the interviews in relation to issues of rapport, linking these whenever possible to the interactional segments they relate to.

Case study 1: a relationship-focused and polite user

1 Hi Miriam, I’m Asa your virtual receptionist from University Of   Surrey. Here is how I can

2 help. 3 I can *schedule* appointments, help you *prepare* for your appointment or answer a *question* you

5 Hello, I was wondering if I could book an MRI scan?

Miriam (a pseudonym) was a participant in the second stage of the project. Example (1) is the start of the interaction with Asa, the bot (l. 1–3).

1 Sure, what date works for you?

2 I can do any day next week other than Wednesday

3 Please pick a time 08:00 09:00 10:00 11:00 12:00 13:00 14:00   15:00 16:00 17:00 18:00 19:00

5 What day?

6 Did you mean? clinic’s *opening times* *hello* *prepare* for appointment *None* of these

7 None of these

8 Sorry, I didn’t quite get that. I’m still learning. Can you please   rephrase the date/time you

9 provided? Thanks, Asa

10 Tuesday would be best

11 Sorry, I didn’t understand that. Can you say that in a different way?

12 Can I have the scan on Tuesday

Miriam reacts to Asa’s introduction by greeting Asa (‘hello’) and with a request to book an MRI scan. The request is made as a conventionally indirect request, with ‘I am wondering’ forestalling the actual request (l. 4).

Example (2) is taken from Miriam’s booking interaction with Asa. After Asa’s prompt to provide a date (l. 1), Miriam indicates her availability, though the only ‘named’ day within her turn is the day when she is not available (l. 2). This causes Asa to move the conversation on to the next question about preferred appointment times (l. 3). Given the lack of clarity with regard to the day of the appointment, Miriam reacts by asking a question to confirm what day the appointment will take place (l. 5). Asa does not understand and requests repair (l. 6), to which Miriam reacts by using one of Asa’s prompts from the previous turn (l. 7). Miriam subsequently reacts to Asa’s second and third repair request (l. 8-9, l. 11) by attempting again to confirm a day of the appointment. Both requests include negative politeness marker, for example, ‘would be’ (l. 10) and ‘can I have’ (l. 12).

14 Okay. Please let me know the number of the appointment you would like to cancel: 1.

Example (3) represents a point in the interaction at which Miriam is trying to ask questions about the procedure. After her question about actions to take ahead of the procedure (l. 1) is not understood by Asa (l. 2), she provides a ‘repaired’ turn twice (l. 3, 6). Asa does not understand Miriam’s new information request (l. 11) prompting Miriam to move out from the information-seeking sequence into a cancellation sequence. When making the cancellation request she does so again in a conventionally indirect manner (‘can I cancel’, l. 13).

Case study 2: a task-focused user

John (also a pseudonym) also interacted with Asa during the survey stage of the project. Example (4) showcases John’s complete booking interaction with Asa.

1 Hi John, I’m Asa your virtual receptionist from University Of Surrey.   Here is how I can help. I

can 2 *schedule* appointments, help you   *prepare* for your appointment or answer a

*question* you   may 3 have

5 Sure, what date works for you?

7 Okay. you can choose the time of day you want for your appointment: • Morning (8am-12pm)

• 8 Afternoon (12pm-5pm) •   Evening (5pm-8pm) • Any (8am-8pm)

10 Please put in your preferred time 08:00 09:00 10:00 11:00   None

12 I can offer you these appointment times 08:00 09:00 10:00 11:00   None

14 Hi John. I’m Asa, your virtual receptionist. Happy to confirm your   Screening appointment is

now15 booked for Wed 23 Mar ‘22 at   10:00. Is this ok?

After Asa’s standard introduction (l. 1–3), John’s first turn consists of only one word, indicating his need to schedule an appointment (l. 4). As the interaction progresses, John’s subsequent answers are equally short. For example, his requests include no additional politeness markers (e.g. l. 6), and he also uses Asa’s own prompts from the previous turn to progress the interaction (e.g. ‘morning’, l. 9). This is particularly evident when his original date input is not understood by Asa (l. 11), and he subsequently reverts to a time format that is more acceptable to Asa (l. 13). This leads to successful confirmation of the appointment (l. 14–15).

2 •You’re welcome to bring a friend or a relative with you • The radiography team with explain

3 the process once you arrive • Please tell us about any special circumstances (for example, if

4 you need wheel-chair access, if you are hard of hearing, if you have poor eyesight or if you are

5 claustrophobic) Do you have any other questions or concerns about what to expect on the

7 Directions

8 Here you go...

2 Okay. Please let me know the number of the appointment you would like to cancel: 1.

3 Screening on Wed 23 Mar ‘22 at 10:00

5 Could you tell us why you have cancelled your appointment? Was it related to: 1. Work

6 commitments 2. Transport issues 3. Concerns regarding the appointment 4. Appointment no

7 longer needed 5. Other

Example (5) is from a sequence in which John asks questions about the preparation for the appointment. He does so without any further politeness markers in a one-word turn (‘prepare’, l. 1). Similarly, he makes his request for directions in only one word, too (l. 7).

When cancelling his appointment (example 6), John makes the same stylistic choices as observed previously. He makes a request for cancellation of one single word (‘cancel’, l. 1), and subsequently uses Asa’s own prompts, in this case, the numeric indicators of preference from the previous turn to proceed with the cancellation sequence (e.g. l. 4, l. 8).

These examples from John’s interaction with Asa show that Miriam and John use different linguistic means to fulfil the same tasks. Miriam greets Asa as if ‘she’ is a human and makes the vast majority of her requests with negative politeness markers. These mitigate the force of the request, indicating that the requests might constitute an imposition on the addressee. Hence, Miriam uses similar strategies to those she might use with a human addressee to whom a request might indeed constitute a face-threatening act that limits their freedom of action.

In contrast, John makes his requests with minimal turns, using just a simple keyword. He is also very adept at using Asa’s own prompts when they are provided, a strategy which can be described as ‘upward convergence’ or ‘accommodation’ to the bot ( Giles and Ogay 2007 : 295). Hence, John uses strategies that are different from what one might expect in face-to-face social interaction. The differences between Miriam’s and John’s strategies may mean different things. One could see them as an indication that Miriam positions Asa as a human, while John perceives Asa as dehumanized and thus not worthy of the social conventions that are the norm when speaking to a human addressee. However, as discussed previously ( Dippold 2023 ), these differences could also be due to the fact that Miriam is a less experienced bot user than John and thus less aware of the sociolinguistic environment human–chatbot interaction represents.

Rapport expectations, rapport threat, and beliefs about language

As discussed in the literature review, Spencer-Oatey’s rapport management framework consists of three interrelated dimensions: face, sociality rights, and interactional goals. I will now use the insights from the thematic analysis to discuss each of these aspects in turn.

Face: Users’ rapport expectations can be threatened when language and interaction patterns do not support users’ face needs or wants. This is shown in example (7) and the respective user comment on the example:

1 We want to ask a few simple, medical questions before the scan. Do you have 2–3 min now to

2 a nswer some questions? This is   for your safety. Please reply with yes/no

4 Thanks. These safety questions take just 3 min, and help us ensure everything is set up

5 correctly

6 1.00/0. Do you have a cardiac (heart) pacemaker? Yes/No

User comment (1)—relating to example (7):

I feel this question is pretty like out of the blue is very like cardiac output peacemaker. I think it’s quite like it has nothing to do with for why I wanted the MRI. I feel like it’s just really random and kind of it doesn’t make sense this has nothing to do with your why I contacted them in the 1st place so I don’t know why they. It just makes me feel like I don’t know why they want me to tell them about this.

Example 7 is from the first part of the medical screening questionnaire, with the first question inquiring whether the user has a cardiac pacemaker. The user (see user comment 1) perceives this as a threat to rapport because of the immediacy of the question and the lack of explanation of its relevance, leading to threat to negative face due to the perceived imposition caused.

Also relating to the medical screening questionnaire was a user comment from the survey:

User comment (2):

It was easy to do but seemed quite robotic and impersonal. When I answered yes to questions I was expecting Asa to ask me for further information or details but she didn’t. It also didn’t give me the opportunity to provide further details e.g., what if my answer wasn’t just Yes or No. The answers left no space for in between answers/grey areas.

This user reports a perceived threat to rapport on the dimension of a positive face because of Asa’s perceived ‘impersonal’ style, which does not allow for the user’s want for connection to be satisfied. This is linked specifically to the lack of follow-up questions by Asa on affirmative answers to the medical screening questions, and the fact that the questions and answers did not leave any room for vagueness.

Sociality rights.

In addition to rapport threat based on ‘face’, user comment (2) can also be read as threatening rapport on accounts of equity rights as the lack of room for elaboration shows a lack of consideration for the users’ needs. Indeed, many of the comments in both surveys and interviews discuss rapport threat based on perceived equity rights violations, such as when a question is not answered (user comment 3) or Asa displays a lack of understanding (user comment 4):

User comment (3):

They ignored my question completely and it made me agitated.

User comment (4):

Too robotic, only understands key words from my phrases, I had to send at least 3 messages for her to understand what I meant.

Cost–benefit considerations come into play in some user comments:

1 What date works for you?

2 4/02/2022

3 Our clinic is open Monday through Friday only. Please try specifying   a date that does not

4 fall on weekends.

6 Please choose a convenient time of day - any - Morning - Afternoon   - Evening

8 Please choose a time slot 09:00 10:00 11:00 None

User comment (5)—relating to example (8):

For example, I think I don’t like the idea for it. I I am just giving a day Tuesday, for example, but I still can’t. No exactly which date is available can be the 8th of Tuesday the 8th. It can be 11. Choose day, so, uh, it’s a bit overwhelming because I can be available on that day, but I may not be available. May have other responsibilities other days, so I cannot speak exactly at 8. I think I am looking for more freedom to choose the time the date exactly.

This user (user comment 5) bemoans the fact that the booking dialogue does not afford sufficient opportunity for consideration of their needs. Whilst Asa offers a date, there is no certainty that the user is available at the specific time(s) offered by Asa. The user thus felt that their personal freedom to make choices was restricted—an issue also relating to negative face—making the dialogue quite ‘costly’ in terms of the effort required to achieve a successful booking.

There are also user comments that indicate rapport being threatened based on association rights:

User comment (6):

Quick and easy. Although I selected option 3 ‘concerns regarding the appointment’ and it didn’t prompt me to discuss my concerns or call anyone. That might leave me up in the air as a worried potential patient not sure who to turn to for advice.

This user describes Asa’s lack of response to their indicating that they had concerns about the appointment. These concerns were neither addressed by Asa nor did a human respond to them in a follow-up call. This goes against this user’s perceived rights to an association with a medical service provider who responds to patient concerns.

Interactional goals.

This rapport dimension is concerned with whether users have a mainly relational or a mainly transactional orientation to the interactions with Asa. In the analysis of interviews ‘efficiency’ emerged as an important need reported by users, betraying a transactional orientation focussed primarily on achieving task goals quickly and efficiently. This is in opposition to another user need described through the theme of ‘personalization’. User comments 7 and 8 and their associated interaction transcripts illustrate these contrasting user needs and goals:

User comment (7)—relating to example (9):

I think because they just went straight like oh hi and they just meet and they didn’t really introduce themselves. I kind of thought like OK this is kind of looked like a robotic response and also kind of like when they said please choose a convenient time for you. Please choose. It’s kind of like no one’s there, it’s just the automatic responses. Please choose like I think if it was someone behind the text, I think they’d be more like oh can you or I don’t know, it’s just something a bit more humanely kind of, not just kind of that direct.

1 Hi Test, I’m Asa from—Asa Clinic, your clinic assistant. Here is how   I can help. Just type:

2 *Schedule/ Reschedule/ Cancel* - Book New/Manage existing   appointment(s) *Prep* -

3 For info on how to prepare for your appointment *FAQ* - For our   frequently answered

4 questions page *General* - For general info (opening times, phone   no., directions/maps etc.)

5 *Admin* - To speak with someone

7 Hi Test, Is there anything I can help you with?

8 I would like to book an MRI appointment please

9 What date works for you?

10 Can I book it for the 28th January

In relation to example (9), this user discusses their need for a more personalized experience to fulfil core interpersonal/social goals of the encounter, perceiving the dialogue overall as rather ‘robotic’ and expressing a wish for it to be less ‘direct’ and involving more direct forms of address, for example, ‘can you’. It is interesting to note that the user here also betrays an overall anthropomorphic orientation to the dialogue, as evidenced by them greeting Asa (l. 6) and their use of politeness strategies in their booking request (l. 8).

Reflecting on their own interaction with Asa, another user displays a more transactional orientation:

User comment (8):

In theory this would be great because all I know is that if it was working then I’m not waiting around. I can ask and see what my options are boom and then I have my appointment over and done with without having to wait through a waiting time. And I’ve also got proof as well over the text message to show that even though they’re hopefully will send me a confirmation message. There’s also proof via the text that they have texted me saying these are my options and that’s the option that I’ve chosen.

This user emphasizes primarily the speed and efficiency with which appointments are made by Asa compared to booking appointments with the help of a human receptionist. Part of that appreciation for efficiency is also the fact that, given the interaction is recorded in written form, there is a record of the booking.

In addition, the data also revealed instances in which users orient in parallel to social and transactional goals and value both the anthropomorphic and the robotic features of social interaction.

User comment (9):

Yeah, because I did this kind of like interaction before. I know like the procedure and I know like this is not a real person so the responding speed is it’s good. You know they’re not like holding back to process the information I type in. So maybe the AI smart. It’s smart enough to go through the process. And second, you know the languages for me is. Understandable, it’s clear. but however I like, I said before like they don’t have like this small talk like they don’t have like opening talk that to to make the people who want to book appointment feel welcome, I feel like. but this is it’s pretty good. It’s pretty good. Yeah, because it’s super convenient.

In comment (9), the user, on one hand, expresses appreciation for the effectiveness and speed by which bookings can be made. On the other hand, they also comment on the fact that, in the earlier stages of the interaction, Asa the bot offers hardly any small talk to make the user feel welcome. This shows that conflicting rapport orientations and language beliefs can co-exist within individuals. These may in turn be reflected within their ‘practiced’ orientations.

This paper aimed to answer the following two central research questions:

What pragmatic strategies people use when interacting with chatbots?

The data presented above show that, even though most users taking part in this project are from a similar demographic group, their pragmatic strategies show considerable variation. They also show that, at times, these strategies contravene expectations. For example, users may talk to Asa as if they were a human—using politeness features as if trying to protect Asa’s face, referring to the Asa by name—even when Asa does not understand their input and is ineffective in completing the task. This suggests that some users are finding it difficult to detach themselves from ‘learned’ human–human interaction behaviours. This project did not investigate whether users’ pragmatic strategies change depending on whether Asa is more or less anthropomorphized, but this is a possible topic for further investigation.

Moreover, the data show that, if Asa’s language and interaction patterns fail to align with users’ rapport expectations, users are likely to have more negative experiences of their interactions. These of course have the potential to disengage users from interacting with bots. It is highly likely that, in a more diverse user group, differences in users’ expectations and practices would likely be even more pronounced. Moreover, in a real-life context with more at stake, users’ negative experiences and perceptions of their expectations being unmet would have been exacerbated and led to disengagement and dissatisfaction with the service.

What is audience design for chatbots and why is it needed?

Interactional sociolinguistics research in professional contexts has revealed that variation in language practices and in perceptions of appropriateness can lead to inequalities, for example in terms of access of linguistic minorities to the job market ( Roberts 2021 ). Research by the King’s Fund (2020) also warned that inequalities in access to and experience of health services can arise because ‘information is not communicated in an easily understandable or culturally sensitive way’. Given the growing importance of chatbots in commercial as well as public service contexts including the health services, it is vital that this situation is not mirrored when services—such as, in this simulated example, medical appointment booking—are delivered through and accessed through chatbots.

This paper has shown that, whilst users’ pragmatic practices and preferences vary, Asa’s contributions to the dialogue remain stable, however, users interact with them. I argue that to provide all user groups with a good user experience, and thus equal access to services delivered by chatbots, chatbot design needs to take account of a diversity of expectations through audience design, focussing in particular on meeting users’ rapport expectations. I define audience design for chatbots as follows:

Audience design for chatbots is the adaptive design of chatbot language and interaction patterns in response to the chatbot user.

Examples of adaptive design might include the following (in a non-exhaustive list):

Politeness strategies used by the chatbot, e.g. when making requests to the user or apologizing to the users asking for an apology. Research on cross-cultural pragmatics in human–human interaction (see e.g. House and Kadar 2021 ) has demonstrated clearly that there is cross-cultural variation in the way politeness strategies are produced and perceived. Therefore, there is every reason to assume that there is variation in chatbot users’ preferences across user groups.

Phatic elements, such as greetings, partings, backchannels are used in conversation to establish social contact between participants. Kulkarni (2013) , exploring phatic elements in instant messaging interactions, argues that ‘it is possible that data sets belonging to different cultures will suggest different requirements of contact’ (134). This suggests again that adaptive design of phatic elements in chatbot dialogue might be able to better engage specific user groups.

Adaptive user support: As the two examples from the case studies have shown, some users use pragmatic strategies that are conducive to effective interaction with chatbots, whereas other users apply strategies that are less effective (see also Dippold 2023 ). Adaptive dialogue design for chatbots would include the bot recognizing which user will need more assistance, and consequently provide this assistance, for example by making the ‘rules of the game’ more explicit, in particular on what strategies to use to ensure the bot understands etc.

Engaging in audience design goes some way toward making chatbots user- rather than technology-centred ( Kopp and Krämer 2021 ). Microsoft’s (2019) guidelines for human-AI interaction design, already include references to audience design, for example, ‘Match relevant social norms: Ensure that experience is delivered in a way that users would expect, given their social and cultural context’ and ‘Mitigate social biases: Ensure the AI system’s language and behaviours do not reinforce undesirable and unfair stereotypes and biases’.

This view is supported by Sutton et al .’s ( 2019 ) research on sociophonetic design strategies in the development of voice–user interfaces such as Siri and Amazon Alexa. The authors argue that the VUI voices need to be ‘designed for diversification’ (11), considering users’ voice-based preferences. They also argue that there is a need ‘to focus on developing tools and techniques that allow the mining of and inference of voice-based preferences, while also dynamically respond to users’ (12). I will use the next section of this paper to propose that the same considerations also apply to text-based conversational AI and to describe a research agenda that supports this purpose.

A research agenda for audience design

When the conversational pathways of chatbots are scripted and defined, this is usually done with the support of conversation designers. Based on the data analysed in this paper, I purport that audience design should be seen as an aim as well as an outcome of conversation design. As an aim , audience design is able to support principles of inclusive design, defined as ‘design that considers the full range of human diversity with respect to ability, language, culture, gender, age and other forms of human difference’ ( Deibel and Evanhoe 2021 : 270). In the UK, the Equality Act ( National Archives 2010 ) stipulates that public bodies, including the NHS, have a duty to eliminate discrimination and advance equality of opportunity. Whilst the Equality Act does not include language as a protected characteristic, it does include age and race, which, as the literature review has shown (e.g. Gumperz 1982 ; Følstad et al. 2020 ; Van der Goot 2021 ) has links to language-based preferences.

As an outcome , effective audience design needs to be underpinned by methods and approaches that allow for true user-centredness. To achieve this, ethnographic approaches that investigate user interactions with AI, and investigations that focus on user perceptions need to move out of simulated and experimental environments (see literature review) into real-life contexts in order to truly reflect the user experiences when higher stakes area attached to a task. In addition, co-design methods ( Steen 2013 ) need to be adapted to exploring the influence of wider social factors on users’ pragmatic strategies and preferences. In the case of chatbot dialogue, users would be involved with writing how they imagine the optimal dialogue to be. Finally, as I have argued previously ( Dippold et al. 2020 ), any research that has the purpose of underpinning audience design for chatbots will additionally benefit from analysis of user–bot interactions to provide differentiated insights into users’ rapport expectations and pragmatic practices. Previous studies suggest that the success of chatbot dialogue is influenced by how users interact with the system ( Kvale et al. 2019 ) and by users’ degrees of experience in interacting with chatbots effectively ( Dippold 2023 )

There are, of course, possible limitations to audience design in relation to the dynamic recognition of user preferences. As research on human–human interaction has shown, service user identities should not be seen as stable, but as constantly evolving ( Feller 2014 ; Flinkfeldt et al. 2021 ). Adaptive audience design would thus need to use natural language processing to dynamically feed analyses of users’ own pragmatic strategies and preferences into a decision-making module, with the goal of creating chatbot dialogue that dynamically adapts to these strategies and preferences.

Limitations

This study has a number of limitations. It is based on a small dataset of user–bot interactions that were gathered in a simulated rather than a real-life environment. However, the study was not designed to provide empirical proof of how targeted audience design can improve audience engagement and trust. Instead, this study has shown, in a qualitative way, the need for audience design and pathways toward its implementation. In the future, larger empirical studies are necessary to gather data on user–chatbot interactions, to implement audience design, and to then evaluate its success through empirical methods (e.g. O’Brien et al. 2018 ; Gulati et al. 2019 ; Chaves et al. 2022 ).

In addition, Bell’s concept of audience design ( Bell 1984 , 2001 ), which underpins this study, was of course never developed for contexts in which one of the ‘speakers’ is an artificial rather than a human agent. In contrast to humans, chatbots do not have any inherent ability to assess who the audience is and what their practices and preferences may be. The ability to recognize users’ rapport expectations thus needs to be ‘taught’ to bots through a machine-learning approach that extracts codes and infers these based on users’ pragmatic strategies. Braunger et al. (2017) , Cruz-Benito et al. (2017) demonstrate this concept by using machine-learning algorithms to build predictive models of user preferencing and behaviour, allowing a complex survey to be adapted to different users. Whilst this process will of course be subject to its own shortcomings, flaws, and errors, it has the potential to positively support efforts for more equitable participation in commercial and public services delivered by chatbots.

Finally, this study also did not gather data ‘in the wild’, investigating authentic user interactions with a chatbot with a real-life transactional goal (such as booking a medical appointment), but drew on simulated data Whilst this approach puts some limits on the ecologic validity of the results—their generalizability to real-life settings ( Andrade 2018 )—the triangulated, qualitative approach, both in terms of data collection points and analytical perspective used in this study, still constitutes a significant step-change in human–machine interaction research.

This paper had a combined theoretical and practical aim: it has developed the concept of ‘audience design’ for chatbots and other forms of conversational AI, arguing that careful audience design allows AI-based social interaction to consider the needs of specific user groups, moving away from a ‘one size fits all’ approach. Through excerpts from user interactions with AI, user interviews, and surveys it has also shown that insights users’ pragmatic practices and their rapport expectations can provide an ideal underpinning for audience design. With a commitment to audience design, conversational AI can be developed in a people-centric way, increasing user engagement with and enjoyment of bots and related technologies and providing equitable access to services.

Notes on Contributor

Doris Dippold is a senior lecturer in Intercultural Communication at the University of Surrey. She is a fellow of the Surrey Institute for People-Centred AI and co-leads Working Group 8 (Language Variation, Pragmatics, and Interaction) of the Research Network LITHME (Language in the Human Machine Era). She has published extensively on conversational AI, chatbots, intercultural pragmatics, English as a lingua franca, internationalization of higher education, and classroom interaction. Her collaboration with amo.ai led to improvements in dialogue design of a business-to-business chatbot. Currently, she is supporting spryt.com with research on audience design for their medical appointment booking chatbot. Address for correspondence: School of Literature and Languages, University of Surrey, School of Literature and Languages, Guildford GU27XH, UK < [email protected] >

The author wishes to thank Adeeba Ahmad for her support with data analysis and Marion Heron for her feedback on the first draft of the paper.

This work was supported by the University of Surrey ESRC Impact Acceleration Account.

Andrade , C.   2018 . ‘Internal, external, and ecological validity in research design, conduct, and evaluation,’   Indian Journal of Psychological Medicine   40 / 5 : 498 – 9 .

Google Scholar

Aston , G.   1995 . ‘Say “Thank You”: Some pragmatic constraints in conversational closings,’   Applied Linguistics   16 / 1 : 57 – 86 .

Bell , A.   2001 . ‘Back in style: Reworking audience design’ in Eckert , P. and Rickfort , J.  (eds.),  Style and Sociolinguistic Variation . Cambridge University Press ; 139 – 169 .

Bell , A.   1984 . ‘Language style as audience design,’   Language in Society   13 / 2 : 145 – 204 .

Bickmore , T. and R.   Picard .   2005 . ‘Establishing and maintaining long-term human-computer relationships,’   ACM Transactions on Human-Computer Interaction   12 / 2 : 293 – 327 .

Braun , V. and V.   Clarke .   2019 . ‘Reflecting on reflexive thematic analysis,’   Quality Research in Sport, Exercise and Health   11 / 4 : 589 – 97 .

Braunger , P. , Maier , W. , Wessling , J. and Werner , S.   2017 . ‘Natural language input for in-car spoken dialog systems: How natural is natural’ , Proceedings of the SIGDIAL 2017 Conference. Saarbrücken , Association for Computational Linguistics , 137 – 46 .

Brown , S. and Levinson , P.   1987 . Politeness. Some Universals in Language Usage . Cambridge University Press .

Google Preview

Byrne , D.   2022 . ‘A worked example of Braun and Clarke’s approach to reflexive thematic analysis,’   Quality & Quantity   56 : 1391 – 412 .

Chaves , A.  et al. . 2022 . ‘Chatbots language design: The influence of language variation on user experience with tourist assistant chatbots,’   ACM Transactions on Computer-Human Interaction   29 / 2 : 1 – 38 .

Cowan , B.R.  et al. . 2016 . ‘Towards understanding how speech output affects navigation system credibility’ , Proceedings of CHI 2016, San Jose , Association for Computing Machinery , 2805 – 12 .

Cruz-Benito , J.  et al. . 2017 . ‘Enabling adaptability in web forms based on user characteristics detection through A/B testing and machine learning,’   IEEE Access   6 / 2251 : 2251 – 2265 .

Deibel , D. and Evenhoe , R.   2021 . Conversations With Things: UX Design for Chat and Voice . Rosenfeld Media .

Dippold , D.   2023 . ‘“Can I have the scan on Tuesday?” User repair in interaction with a task-oriented chatbot and the question of communication skills for AI,’   Journal of Pragmatics   204 : 21 – 32 .

Dippold , D.  et al. . 2020 . ‘A turn to language: How interactional sociolinguistics informs the redesign of prompt:response chatbot turns,’   Discourse, Context and Media   37 : 100432 .

Feller , S.   2014 . ‘The good, the bad, and the ugly: The co-construction of identities in dialog,’   Language and Dialogue   4 / 3 : 341 – 56 .

Flinkfeldt , M. , S.   Parslow , and E.   Stokoe .   2021 . ‘How categorization impacts the design of requests: Asking for email addresses in call-centre interaction,’   Language in Society   51 : 693 – 716 .

Følstad , A. and P.   Brandtzæg .   2020 . ‘Users’ experiences with chatbots: Findings from a questionnaire study,’   Quality and User Experience   5 / 3 .

Fraser , B.   1999 . ‘What are discourse markers?,’   Journal of Pragmatics   31 / 7 : 931 – 52 .

Giles , H. and Ogay , H.   2007 . ‘Communication accommodation theory’ in Whaley , B. and Samter , W. (eds), Explaining Communication: Contemporary Theories and Exemplars . Lawrence Erlbaum ; 293 – 310 .

Goffman , E.   1971 . Relations in Public: Microstudies of the Public Order . Basic Books .

Gulati , S. , S.   Sousa , and D.   Lamas .   2019 . ‘Design, development and evaluation of a human-computer trust scale,’   Behaviour & Information Technology   38 / 10 : 1004 – 15 .

Gumperz , J.   1982 . Discourse Strategies . Cambridge University Press .

Haugh , M. and D.   Carbaugh .   2015 . ‘Self-disclosure in initial interactions amongst speakers of American and Australian English,’   Multilingua   34 / 4 : 461 – 93 .

Hill , J. , W.   Ford , and I.   Farreras .   2015 . ‘Real conversations with artificial intelligence: A comparison between human-human online conversations and human-chatbot conversations,’   Computers in Human Behavior   49 : 245 – 50 .

House , J. and Kadar , D.   2021 . Cross-Cultural Pragmatics . Cambridge University Press .

Hymes , D.   1974 . Foundations in Sociolinguistics: An Ethnographic Approach . Routledge .

King’s Fund . 2020 . ‘ What are Health Inequalities?,’ available at https://www.kingsfund.org.uk/publications/what-are-health-inequalities . Accessed 21 February 2024 .

Kopp , S. and N.   Krämer .   2021 . ‘Revisiting human-agent communication: The importance of joint co-co-construction and understanding mental states,’   Frontiers in Psychology   12 : 580955 .

Kulkarni , D.   2013 . ‘Exploring Jacobson’s “phatic function” in instant messaging interactions,’   Discourse & Communication   8 / 2 : 117 – 36 .

Kvale , K. , Sell , O. , Hodnebrog , S. , and Følstad , A.   2019 . ‘Improving conversations: Lessons learnt from manual analysis of chatbot dialogues’ in: Følstad , A . et al.  (eds.),  International workshop on chatbot research and design.  Springer International Publishing ; 187 – 200 .

Laver , J.   1981 . ‘Linguistic routines and politeness in greeting and parting’ in: Coulmas , F . (ed.),  Explorations in Standardized Communication Situations and Prepatterned Speech. Volume 2: Conversational Routine . De Gruyter Mouton ; 289 – 304 .

Li , M. and J.   Mao .   2015 . ‘Hedonic or utilitarian? Exploring the impact of communication style alignment on user’s perception of virtual health advisory services,’   International Journal of Information Management   35 / 2 : 229 – 43 .

Microsoft . 2019 . ‘ Guidelines for human-AI interaction design ,’ available at https://www.microsoft.com/en-us/research/blog/guidelines-for-human-ai-interaction-design/ . Accessed 6 March 2023 .

National Archives . 2010 . ‘ Equality act ,’ available at https://www.legislation.gov.uk/ukpga/2010/15/section/149 . Accessed 6 March 2023 .

O’Brien , H. and CairnsHall , M.   2018 . ‘A practical approach to measuring user engagement with the refined user engagement scale (UES) and new UES short form,’   International Journal of Human-Computer Studies   112 : 28 – 39 .

Pelikan , H.   2015 . ‘ How humans adapt to a robot recipient: An interaction analysis perspective on human-robot interaction’, Bachelor thesis, University of Osnabrück .

Pelikan , H. and Broth , M. , 2016 . ‘Why that Nao? How humans adapt to a conventional humanoid robot in taking turns-at-talk’ , CHI ‘16: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, 4921 – 32 .

Roberts , C.   2021 . Linguistic Penalties and the Job Interview . Equinox .

Salem , M. , Yiadee , M. , and Sakr , M.   2014 . ‘Marhaba, how can I help you? Effects of politeness and culture on robot acceptance and anthropomorphization’ , 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI), 74 – 81 .

Spencer-Oatey , H.   2005 . ‘(Im)politeness, face and perceptions of rapport: Unpackaging their bases and interrelationships,’   Journal of Politeness Research   1 : 95 – 119 .

Spencer-Oatey , H.   2008 . Culturally Speaking: Culture, Communication and Politeness Theory . Bloomsbury Publishing .

Spencer-Oatey , H.   2002 . ‘Managing rapport in talk. Using rapport sensitive incidents to explore the motivational concerns underlying the management of relations,’   Journal of Pragmatics   34 / 5 : 529 – 45 .

Spencer-Oatey , H. and Franklin , P.   2009 . Intercultural Interaction: A Multidisciplinary Approach to Intercultural Communication . Palgrave Macmillan .

Spencer-Oatey , H. and J.   Xing .   2003 . ‘Managing rapport in intercultural business interactions: A comparison of two Chinese-British welcome meetings,’   Journal of Intercultural Studies   24 / 1 : 33 – 46 .

Srinivasan , V.   2016 . ‘Help me please: Robot politeness strategies for soliciting help from people’ , CHI ‘16: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, 4945 – 55 .

Steen , M.   2013 . ‘Co-design as a process of joint inquiry and imagination,’   Design Issues   29 / 2 : 16 – 28 .

Sutton , S. , Faulkes , P. , Kirk , D. and Lawson , S.   2019 . ‘Voice as a design Material: Sociophonetic inspired design strategies in human-computer interaction’ , CHI ‘19: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, 1 – 14 .

Timpe-Laughlin , V. and J.   Dombi .   2020 . ‘Exploring L2 learners’ request behavior in a multi-turn conversation with a fully automated agent,’   Intercultural Pragmatics   17 / 2 : 221 – 57 .

Van der Goot , M. , Hafkamp , L. , and Dankfort , Z.   2021 . ‘Customer service chatbots: A qualitative interview study into the communication journey of customers’ in Følstad , A.  et al.  (eds.),  Chatbot Research and Design. 6th International Workshop: Conversations 2020 . Springer ;  190 – 204 .

Waytz , A. , N.   Eplez , and J.   Cacioppo .   2010 . ‘Social cognition unbound: Insights into anthropomorphism and dehumanization,’   Current Research in Psychological Science   19 / 1 : 58 – 62 .

Supplementary data

Email alerts, citing articles via, looking for your next opportunity.

• Recommend to your Library

Affiliations

• Online ISSN 1477-450X
• Print ISSN 0142-6001
• Copyright © 2024 Oxford University Press
• About Oxford Academic
• Publish journals with us
• University press partners
• What we publish
• New features  
• Open access
• Institutional account management
• Rights and permissions
• Get help with access
• Accessibility
• Advertising
• Media enquiries
• Oxford University Press
• Oxford Languages
• University of Oxford

Oxford University Press is a department of the University of Oxford. It furthers the University's objective of excellence in research, scholarship, and education by publishing worldwide

• Copyright © 2024 Oxford University Press
• Cookie settings
• Cookie policy
• Privacy policy
• Legal notice

This Feature Is Available To Subscribers Only

Sign In or Create an Account

This PDF is available to Subscribers Only

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Farmer-led climate adaptation: call for local case studies

• Flagship Programme 1

The Eastern Africa Farmers Federation (EAFF) and AICCRA are calling for submissions on farmer-led best practice case studies that demonstrate innovative local activities and methods to enhance agricultural adaptation and ultimately promote resilience. Deadline for submission: 19 May 2024

The Eastern Africa Farmers Federation (EAFF) in collaboration with Accelerating Impacts of CGIAR Climate Research for Africa (AICCRA), is implementing a project to showcase best practice examples of farmer-led adaptation in managing the negative impacts of climate change on agriculture. These studies will be selected from diverse regions across Africa. The final project output will be a compendium of farmer-led best practice case studies that demonstrate innovative local activities and methods to enhance agricultural adaptation and ultimately promote resilience.

At the project launch, EAFF and AICCRA announced the call for farmer-led best practice case studies that demonstrate innovative local activities and methods to enhance agricultural adaptation and ultimately promote resilience. You can submit your case study by 19 May.

Call for local case studies

EAFF and AICCRA are working towards developing a compendium of farmer-led best practice case studies that demonstrate innovative local activities and methods to enhance agricultural adaptation and ultimately promote resilience across the continent.

Case studies selection

Case studies will be selected from:

• All the geographical regions across Africa
• Will vary in their scale, focus and level of amition

Innovations will be identified and selected in collaboration with local partners, including regional farmer organisations, local communities, NGOs and other appropriate partnners.

Once identified, EAFF and AICCRA will collaborate directly with the grassroots level innovators to document their specific activities and best practices of each project in each unique locality. This includes information that:

• Captures the details of each innovation and describe how it effectively responds to a changing climate;
• Describes the lived reality of each context;
• Defines key challenges and enabling factors for the project's successes and difficulties;
• Gives valuable insights and "key takeaways";
• Provides recommendations on their suitability and potential application in other areas, with the hope to replicate and scale best practices in different regional areas across the continent.

What is required from our partner organisations:

• Assistance to identify farmers, farmer organisations, local agro-businesses in your particular region that are currently demonstrating leadership and good practices in agricultural adaptation to climate change;
• A motivation as to why this particular project demonstrates leadership and innovation;
• A brief introduction of the project to EAFF and AICCRA staff and the sharing of innovator or project contact details;
• Additional information and images that can help describe the innovation or practice.

Further information

If you'd like to know more about the submissions or the project itself, please contact:

Norbert Tuyishime - EAFF Project Officer - [email protected]

Romy Chevallier - AICCRA Policy and Engagement Consultant - [email protected]

About the launch workshop

Objectives:

• Introduce the project, its key objectives and timelines;
• Describe locally led farmer adaptation and provide examples of innovative practices;
• Launch a collaborative call for regional African farmer-led adaptation case studies; and
• Describe the case study selection process and request your support to identify farmers, farmer organisations and local agro-businesses that are demonstrating leadership and good practices in agricultural climate adaptation.

Presentations

• Apercu-du-projet.pdf (2.23 MB)

• Open access
• Published: 06 May 2024

Risk factors for delayed extubation after pediatric perineal anaplasty in patients less than 1 year of age: a retrospective study

• Qianqian Zhang 1   na1 ,
• Jing Xu 1   na1 ,
• Qinghua Huang 1 ,
• Tianqing Gong 1 ,
• Jia Li 1 &

BMC Pediatrics volume  24 , Article number:  307 ( 2024 ) Cite this article

51 Accesses

Metrics details

Anorectal malformation is a common congenital problem occurring in 1 in 5,000 births and has a spectrum of anatomical presentations, requiring individualized surgical treatments for normal growth. Delayed extubation or reintubation may result in a longer intensive care unit (ICU) stay and hospital stay, increased mortality, prolonged duration of mechanical ventilation, increased tracheostomy rate, and higher hospital costs. Extensive studies have focused on the role of risk factors in early extubation during major infant surgery such as Cardiac surgery, neurosurgery, and liver surgery. However, no study has mentioned the influencing factors of delayed extubation in neonates and infants undergoing angioplasty surgery.

Materials and Methods

We performed a retrospective study of neonates and infants who underwent anorectal malformation surgery between June 2018 and June 2022. The principal goal of this study was to observe the incidence of delayed extubation in pediatric anorectal malformation surgery. The secondary goals were to identify the factors associated with delayed extubation in these infants.

We collected data describing 123 patients who had anorectal malformations from 2019 to 2022. It shows that 74(60.2%) in the normal intubation group and 49(39.8%) in the longer extubation. In the final model, anesthesia methods were independently associated with delayed extubation ( P  < 0.05).

We found that the anesthesia method was independently associated with early extubation in neonates and infants who accepted pediatric anorectal malformation surgery.

Peer Review reports

Introduction

Anorectal malformation is one of the general congenital problems occurring in approximately 1 in every 5,000 births and presenting with anatomical variations that require individualized surgical treatment to ensure normal growth [ 1 ]. Low anorectal malformation/rectoperineal fistula may be ignored in the newborn. When symptomatic, it may be corrected by a simple angioplasty with excellent results [ 2 ]. Early tracheal extubation after anesthesia can help rapid intestinal recovery and restore the normal growth and development of infants, as well as improve infant outcomes and lower postoperative complications [ 3 , 4 , 5 ]. Among surgical interventions for infants, anesthesia-related critical events occur at a high incidence rate of up to 3.4% [ 6 ], with respiratory events being particularly common(46.5%) [ 7 ]. For neonates and small infants under anorectal malformation surgery, anesthesiologists’ decisions on the appropriate time of extubation after pediatric gastrointestinal surgery are often challenging from many aspects with regard to complex and rapidly deteriorating situations such as airway obstruction, hypoxemia, and possibly urgent reintubation. However, delayed extubation or reintubation may result in longer intensive care units (ICU) and hospital stays, increased mortality, prolonged duration of mechanical ventilation, increased tracheostomy rate, and higher hospital costs [ 8 ]. Therefore, it is necessary and beneficial to postoperative early extubation for infants.

Extensive studies have focused on the role of risk factors in early extubation during major infant surgery such as cardiac surgery, neurosurgery, and liver surgery [ 9 , 10 , 11 , 12 ]. Many studies demonstrated that there is a significant difference in the proportion and duration of postoperative respiratory for neonates and infants. Wang et al. summarized that for 253 newborns who underwent gastrointestinal surgery, the average length of postoperative mechanical ventilation was 3 days [ 13 ]. A clinical study conducted by Ceelie et al., included 71 newborns and infants undergoing thoracic and abdominal surgery without cardiac surgery, abdominal surgery accounted for 77.5%, of which 40.8% required mechanical ventilation after surgery with a duration of 23–34 h [ 14 ]. However, few articles have mentioned that other minor and medium surgeries also need early extubation for infants. The authors describe their experience of maintaining spontaneous breathing in neonates undergoing Fast-track anesthesia (FTA group) which does not use opioids or muscle relaxants during anoplasty. Extubation time in the FTA group was significantly shorted [ 15 ]. However, no study has mentioned the influencing factors of delayed extubation in neonates and infants in neonatal and infant angioplasty surgery.

The principal goal of this study was to investigate the incidence of delayed extubation in pediatric anorectal malformation surgery. The secondary goal was to identify the factors associated with delayed extubation in these patients. Results can help achieve early extubation by providing evidence on optimizing clinical decision-making and improving outcomes in those patients.

Materials and methods

Study design and participants.

This is a single-center, retrospective case-control study, which has been approved by the Institutional Review Board (IRB) of Chengdu Women’s and Children’s Central Hospital [No. 2022 (100)].

The need for Informed Consent was waived by the Institutional Review Board (IRB) of Chengdu Women’s and Children’s Central Hospital due to the retrospective nature of the study. The study adheres to the applicable Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) standards for observational studies. This study enrolled infants with anorectal malformation who were scheduled for angioplasty, either elective or emergency. Clinical protocol is readily available for all general procedures and can be accessed at each anesthesia station through the Department of Anesthesiology intranet.

Patient population

Inclusion criteria are data for infants who had anorectal malformation surgery between June 2018 and June 2022. Eligibility criteria included neonates and infants (≤ one-yea r- old) who were diagnosed with anorectal malformations and underwent surgical intervention (i.e., angioplasty), scheduled for either elective or emergency.

Infants who were dependent on mechanical ventilation preoperatively; lacked birth or hospital records; had received major surgery involving vital organs oncomitantly, and had major cardiopulmonary diseases were excluded. The infants and newborns with contraindications for caudal anesthesia were excluded. Major cardiac defects were defined as any congenital heart anomaly that requires surgical interventional or cardiac catheterization before discharge from the neonatal intensive care unit (NICU) or pediatric intensive care unit (PICU).

All cases were performed by attending anesthetists with ≥ 5 years of experience in pediatric anesthesia. As a rule in the authors’ institution, only anesthetists with ≥ 5 years of experience attending in pediatric anesthesia can perform anesthesia in neonates.

Anesthesia management

The patients who were diagnosed with anorectal malformations and underwent surgical intervention received general anesthesia (GA) or general anesthesia with caudal anesthesia (GA + CA). The protocol for the management of infants is as follows. An intravenous line was established in the ward. Thermal blankets and appropriate room temperature were prepared before the patients entered the operating room. Spontaneous breathing was maintained in 100% oxygen (4 L/min) initially via a mask. Anesthesia was induced by using fentanyl, midazolam, and cis-atracurium. If the respiratory rate decreased to < 20 breaths/min, mechanically controlled ventilation was rapidly assisted. When the appropriate depth of anesthesia was achieved, endotracheal intubation was performed under a laryngoscope. All of the caudal blocks were administered following the induction of anesthesia. The procedure was performed by the experienced attending anesthetist. If the age of patients is younger than 30 days, lidocaine (1mL/kg [0.5%]) is injected after confirmation in epidural space; otherwise, lidocaine (0.5mL/kg [0.5%]) and ropivacaine (0.5mL/kg [0.2%]) will be given. Anesthesia was maintained with sevoflurane and was discontinued 3 min before the completion of surgery. Procedures in the other group were performed using traditional general anesthesia without caudal block. To ensure safety and improve surgical efficiency, the anesthesiologist decided whether to extubate the endotracheal tube in the surgical intensive care unit (SICU) or the operating room. All patients were transferred to SICU after the operation.

Hemodynamic monitoring

All patients were routinely monitored. In the operation room, electrocardiograph (ECG), non-invasive blood pressure, end-tidal carbon dioxide (ETCO2), pulse oximetry, and body temperature were continuously monitored.

Group and definition of delayed extubation

Additionally, postoperative data including the duration time from the completion of anesthesia to tracheal extubation were classified into two categories: normal(< 6 h) and long extubation (≥ 6 h) [ 16 ]. Lastly, all adverse events were recorded, such as reintubation within the subsequent 24 h.

The indicators of extubation in infants encompassed full consciousness by limb movement, regular breathing, and tidal volume 5–8mL/kg. Perioperative data were retrieved from the database [ 17 ].

Preoperative data collected included age, gender, gestational weeks, birth body weight, diagnosis, prematurity history, surgery and intubation history, coexisting cardiac anomalies, coexisting respiratory diseases, failure to thrive, developmental retardation, American Society of Anesthesiologists (ASA) classification, preoperative oxygen supplements, preoperative hemoglobin.

Intraoperative factors included anesthesia methods, duration of surgery, duration of anesthesia, furosemide exposure, estimated blood loss, fluid infusion and urinary output, blood transfusion, and time of extubation. We also collected the patient’s intraoperative opioids, muscle relaxant drugs and antagonists, and other drug consumption.

Postoperative data collected included incidence of reintubation within 24 h; major complications including caudal anesthesia complications were defined as neurologic (paresthesias or a persistent neurologic deficit), local anesthetic (LA) systemic toxicity, infection, vascular (vascular puncture or hematoma), respiratory (pneumothorax or respiratory depression), catheter malfunction, dural puncture, or other; including death, and post-operative ICU, in-hospital mortality, readmitted within 30 days, and accepted an unplanned reoperation.

Study outcome

The principal goal of this study was to investigate the incidence of delayed extubation in pediatric anorectal malformation surgery. The delayed extubation was defined as more than 6 h (≥ 6 h), which was in line with the study of Lamoshi A, et al. The secondary goals were to identify the factors associated with delayed extubation in these patients.

Statistical analysis

In the analysis, categorical variables were represented by number and percentage (%), while continuous variables were represented by mean and standard deviations (mean ± SD) or median and range (min–max). Univariate analysis was used for comparing two categorical variables by chi-square test or Fishers Exact test, and two continuous variables were tested by independent sample t-test or Mann-Whitney U test. The variables associated with delayed extubation ( P  ≤ 0.1) by univariate analysis were included in the multivariate logistic regression for identification of predictive risk factors. Adjusted odds ratio and 95% CI were reported. A P -value of < 0.05 was considered statistically significant. All statistical analyses were performed by SPSS software, version 22.0 (IBM Corp., Armonk, NY, USA).

Baseline characteristics

The study flowcharts are displayed in Fig.  1 . Data describing 128 patients who had anorectal malformations from 2019 to 2022 were collected. From the remaining 128 patients, 1 patient was excluded due to inadequate data; 4 patients who met the exclusion criteria were deleted. Thus, 123 patients were enrolled in the final analysis. According to the definition of delayed extubation, there were 74 (60.2%) cases in the normal intubation group and 49(39.8%) in the longer extubation group.

Independent variables and analysis of risk factors

A total of 123 pediatric patients were included in our study. Table  1 summarizes the baseline characteristics of patients. The incidence of delayed extubation postoperative transfusion of the normal extubation group was 60.16%(74/123). Preoperative factors that had statistically significant differences were age group, body weight, intubation history, preoperative hemoglobin, and ASA (Table  1 ). There was no statistical significance in sex and confidence of comorbidity including PDA, anemia, and premature infants.

Participants flow diagram

The intraoperative factors including anesthesia methods, tube time, duration of surgery, use of muscle relaxants were statistically associated with the delayed extubation group. Duration of anesthesia, volume of blood loss, fluid, urine output, and the use of opioid and muscle relaxant antagonism, ventilation mode, and comorbidity have not been statistically associated with delayed extubation (Table  2 ). Outcomes including postoperative transfusion and postoperative complication have no statistically significant differences (Table  2 ). The variables with P  < 0.1 were entered into stepwise multiple logistic regression models to delayed extubation.

In the univariate analysis, age, weight, preoperative HB, ASA status, anesthesia methods, intubation history, operation time, use of muscle relaxant, and PLOS were independently associated with delayed extubation statistically (Table  2 ).

The variables with P  < 0.05 were entered into stepwise multiple logistic regression models to predict delayed extubation. Multivariable logistic regression analysis (Table  2 ) identified that only anesthesia methods (OR, 0.316; 95%CI, 0.105,0.9903; P  < 0.05) were the independent risk factors for delayed extubation. These factors including Age, weight, preoperative HB, ASA status, intubation history, operation time, and use of muscle relaxant have no statistical significance for delayed extubation by stepwise multiple logistic regression models.

It is very important to achieve early extubation in neonates and infants who underwent pediatric perineal anoplasty [ 5 ]. Our study found that anesthesia methods were independently associated with delayed extubation.

The incidence of delayed extubation after pediatric perineal angioplasty

Compared with adults or older children, neonates and young infants are at a higher risk for delayed extubation. The incidence of delayed extubation in preterm or high-risk infants is 17.2–35.7% in different reports; this variation could depend on the definition of delay, patient characteristics, anesthetic agents used, and whether muscle relaxant was used or not [ 18 , 19 , 20 ]. Obviously, the incidence of delayed extubation varies greatly in different types of surgery. Previous studies have primarily focused on delayed extubation in major pediatric surgery, such as cardiac surgery, neurosurgery, and liver surgery. For pediatric cardiac surgery, the extension of invasive mechanical ventilation time after surgery ranges from 3 to 7 days; for pediatric liver transplantation surgery, the time ranges from over 24 h to 4 days [ 21 , 22 ]. Nafiu et al. proposed to define the extension of invasive mechanical ventilation time as more than 4 days, so 75% of patients are defined as delayed extubation [ 20 ]. Unfortunately, there were few studies about the incidence of early extubation after gastrointestinal surgery in neonates and infants. Our study summarized a total of 123 newborns and infants who underwent congenital anorectal surgery. Surprisingly only 49(39.8%) neonates or infants can achieve normal extubation successfully. Theoretically, congenital anorectal surgery is not a large surgery patients have a higher incidence of early extubation. Yet the incidence of delayed extubation after pediatric perineal angioplasty is 60.7% in our institution. Although theoretically, extubation is not difficult in this perineal angioplasty, in practice especially early extubation in neonates and infants less than one year is not so easy especially in non-children’s specialized hospital, despite infants undergoing uniform anesthesia management in the same institution. So the extubation of infants and newborns should be cautious during anesthesia management of non-major surgery.

Risk factors associated with delayed extubation after pediatric perineal angioplasty

It is well known that demographic characteristics, surgical services, and intraoperative features are associated with delayed extubation. In our study, we observed a significant impact of different anesthetic techniques on the incidence of early extubation in patients with congenital anorectal. Previous research has demonstrated that general anesthesia is linked to higher perioperative adverse events such as apnea and bradycardia compared with spinal anesthesia in preterm infants receiving inguinal hernia repairs [ 19 , 23 ]. Guess general anesthesia combined with caudal anesthesia (GA + CA) can reduce the requirement of anesthetics to achieve early extubation. Regional anesthesia is preferred rather than general anesthesia for preterm infants receiving the hernia surgery in early infancy with lower postoperative respiratory complications, but these comparisons mainly focused on the general anesthesia with endotracheal intubation [ 24 , 25 , 26 ]. Neuraxial anesthesia in neonates and infants is safe and effective [ 27 ]. One study found only 1 serious complication(meningitis) in a neonate in a series of 2490 cases [ 28 ]. Other research shown that 1 neonate of 18,650 children suffered from seizure [ 29 ]. So there were no permanent sequelae and mortality. Effective use of caudal anesthesia can provide perfect analgesic when performed properly. If patients can benefit from caudal anesthesia or region block, anesthesiologists consider applying combined anesthesia in the non-major operation of infants or newborns.

By comparison, some studies have suggested that anesthetic drugs and dosage levels might influence the determination of delayed extubation [ 30 ]. Yet results of other studies found that anesthetic techniques (inhalation or total intravenous anesthesia), nitrous oxide uses, opioid uses were not associated with delayed extubation [ 31 ]. Muscle relaxant did show statistical significance in the univariate model, but it did not retain significance in the multivariate analysis. Our study suggested that anaesthetics including fentanyl drugs had little effect on extraction time. However other studies prompt the opposite result [ 9 ]. These might be due to the heterogeneity of surgical procedures and the diversity of patients’ ages in the previous studies which are different from our population in this retrospective study.

The newborns did show statistical significance in the univariate model, but it did not retain significance in the multivariate analysis. Despite a lack of worldwide consensus, most studies have found that low birth weight (LBW) at the time of the operation and young age (< 6 months) are related to longer extubation [ 32 ]. It indicates that young age is an independent risk factor for delayed extubation after pediatric cardiac surgery [ 21 ]. The reasons are poor fatigue resistance, the endurance of respiratory muscles and immature respiratory center with poor response to hypoxia and hypercarbia [ 33 ]. However, most recent studies, including ours, have failed to find risk factors significant for delayed extubation example for age [ 17 ]. The authors found that other risk factors, in association with young age, increased the risk of delayed extubation rather than age alone. Moreover, the authors comment that it is the decision of the anesthetist and intensivist rather than the patient’s age, which is responsible for the delay in the extubation of newborns especially [ 33 ].

However, our finding did not demonstrate any significant association between intubation history and factors contributing to delayed extubation in pediatric patients. Nevertheless, the study revealed that children with a history of extubation experienced an increased risk of prolonged extubation time [ 9 ].

The potential explanation for these results is that the different institutions or countries have varying factors influencing extubation. Thus we choose a standardized approach to investigate the risk factors associated with delayed extubation in order to minimize confounding variables. These factors may guide anesthesiologists in optimizing anesthesia management for early extubation in similar surgical procedures. For example, applying region block during surgery can achieve early extubation and ensure patient safety. Scheduling extubation within office hours might enhance patient safety and effective resource utilization. Achieving early extubation in infants and newborns, not only helps in the early mobilization of the patient and reduces parental anxiety, but also lowers the cost of patient care and maximizes the utilization of limited hospital resources [ 33 ].

This study has several limitations that may limit its generalizability. Firstly, due to differences in patient characteristics between the two groups in this retrospective survey, we can only conclude that anesthesia methods may impact early extubation in infants and further randomized study is needed. Secondly in the study hospital’s independent clinical management processes and individualized decisions made by each anesthesiologist might introduce selection bias for the clinical outcomes. Thirdly the small sample size could potentially limit the validity of the conclusions, especially difficulty conduct an effective stratified analysis of the age of grouping infants and neonates. Fourthly, however, our previous work included both elective and emergency surgical intervention, which could be susceptible to selection bias. Finally, there are limited variables related to baseline clinical condition and intraoperative course included in our research, posing a high risk of unexplored confounding factors.

Our study is the first analysis of risk factors associated with delayed extubation in patients less than 1 Year of Age: undergoing low anorectal malformation/rectoperineal fistula disorders. We found that type of anesthesia was independently associated with early extubation in neonates and infants who accepted pediatric anorectal malformation surgery. We wish this study can help to achieve early extubation and improve clinical decision-making.

Data availability

Datasets generated during and/or analyzed in the current study are available upon reasonable request to the corresponding author.

Abbreviations

Neonatal intensive care unit

Surgical intensive care unit

Pediatric intensive care unit

Fast-track anesthesia

Wood RJ, Levitt MA. Anorectal Malformations. Clin Colon Rectal Surg. 2018;31(2):61–70. https://doi.org/10.1055/s-0037-1609020 . Epub 2018 Feb 25.

Whyte C, Canty TG, Smith J, Melody K. Anoplasty for low anorectal malformation. J Pediatr Surg. 2016;51(10):1602–6.

Article   PubMed   Google Scholar  

Bruder NJ. Awakening management after neurosurgery for intracranial tumors. Curr Opin Anaesthesiol. 2002;15(5):477–82.

Bruder N, Stordeur JM, Ravussin P, et al. Metabolic and hemodynamic changes during recovery and tracheal extubation in neurosurgical patients: immediate versus delayed recovery. Anesth Analg. 1999;89(3):674–8.

Article   CAS   PubMed   Google Scholar  

Söderström F, Ågren J, Sindelar R. Early extubation is associated with shorter duration of mechanical ventilation and lower incidence of bronchopulmonary dysplasia. Early Hum Dev. 2021;163:105467.

De Graaff JC, Sarfo MC, van Wolfswinkel L, et al. Anesthesia-related critical incidents in the perioperative period in children; a proposal for an anesthesia-related reporting system for critical incidents in children[J]. Paediatr Anaesth. 2015;25(6):621–9. https://doi.org/10.1111/pan.12623 .

Tsogiannaki S, Huang SX, Lukovits K, et al. The characterization of postoperative mechanical respiratory requirement in neonates and infants undergoing cardiac surgery on cardiopulmonary bypass in a single tertiary institution[J]. J Cardiothorac Vasc Anesth. 2022;36(1):215–21. https://doi.org/10.1053/j.jvca.2021.04.023 .

Article   Google Scholar  

Rothaar RC, Epstein SK. Extubation failure: magnitude of the problem, impact on outcome, and prevention. Curr Opin Crit Care. 2003;9(1):59–66.

Nivatpumin P, Srisuriyarungrueng S, Saimuey P, Srirojanakul W. Factors affecting delayed extubation after intracranial surgery in Siriraj Hospital. Siriraj Med J. 2010;62(3):119–23.

Google Scholar  

Raksakietisak M, Keawsai T, Sirivanasandha B. Factors related to delayed extubation in cervical spine surgery in an academic hospital: a retrospective study of 506 patients. Asian J Anesthesiol. 2019;57(4):111–6.

PubMed   Google Scholar  

Anastasian ZH, Gaudet JG, Levitt LC, Mergeche JL, Heyer EJ, Berman MF. Factors that correlate with the decision to delay extubation after multilevel prone spine surgery. J Neurosurg Anesthesiol. 2014;26(2):167–71.

Article   PubMed   PubMed Central   Google Scholar  

Sangtongjaraskul S, Chokengarmwong N, Pornwilaikun P, Paarporn P. Incidence and predictive factors Associated with delayed Extubation after Pediatric Neurosurgery. Asian J Anesthesiol. 2022;60(4):155–63.

Wang H, Gauda EB, Chiu P, et al. Risk factors for prolonged mechanical ventilation in neonates following gastrointestinal surgery[J]. Transl Pediatr. 2022;11(5):617–24. https://doi.org/10.21037/tp-22-14 .

Ceelie I, de Wildt SN, van Dijk M, et al. Effect of intravenous Paracetamol on postoperative morphine requirements in neonates and infants undergoing major noncardiac surgery: a randomized controlled trial[J]. JAMA. 2013;309(2):149–54. https://doi.org/10.1016/j.accpm.2016.05.012 .

Cui Y, Wang Y, Cao R, Liu K, Huang QH, Liu B. On-table extubation in neonates undergoing anoplasty: an experience of anesthetic management on the concept of fast-tracking anesthesia: a pilot study. Med (Baltim). 2019;98(2):e14098.

Article   CAS   Google Scholar  

Lamoshi A, Lerman J, Dughayli J, Elberson V, Towle-Miller L, Wilding GE, Rothstein DH. Association of anesthesia type with prolonged postoperative intubation in neonates undergoing inguinal hernia repair. J Perinatol. 2021;41(3):571–6.

Veyckemans F. Tracheal extubation in children: planning, technique, and complications. Paediatr Anaesth. 2020;30(3):331–8.

Somri M, Gaitini L, Vaida S, Collins G, Sabo E, Mogilner G. Postoperative outcome in high-risk infants undergoing herniorrhaphy: comparison between spinal and general anesthesia. Anesthesia. 1998;53(8):762–6.

Kim GS, Song JG, Gwak MS, Yang M. Postoperative outcome in formerly premature infants undergoing herniorrhaphy: comparison of spinal and general anesthesia. J Korean Med Sci. 2003;18(5):691–5.

Gurria J, Kuo P, Kao A, Christensen L, Holterman A. General endotracheal vs. non-endotracheal regional anesthesia for elective inguinal hernia surgery in very preterm neonates: a single institution experience. J Pediatr Surg. 2017;52(1):56–9.

Polito A, Patorno E, Costello JM, Salvin JW, Emani SM, Rajagopal S, Laussen PC, Thiagarajan RR. Perioperative factors associated with prolonged mechanical ventilation after complex congenital heart surgery. Pediatr Crit Care Med. 2011;12(3):e122–6. https://doi.org/10.1097/PCC.0b013e3181e912bd . PMID: 0625334.20.

Maldonado G, Greenland S. Simulation study of confounder-selection strategies[J]. Am J Epidemiol. 1993;138(11):923–36. https://doi.org/10.1093/oxfordjournals.aje.a116813 .

Ponde VC, Bedekar VV, Desai AP, et al. Does ultrasound guidance add accuracy to continuous caudal-epidural catheter placements in neonates and infants? Paediatr Anaesth. 2017;27:1010–4.

Dohms K, Hein M, Rossaint R, Coburn M, Stoppe C, Ehret CB, et al. Inguinal hernia repair in preterm neonates: is there evidence that spinal or general anaesthesia is the better option regarding intraoperative and postoperative complications? A systematic review and meta-analysis. BMJ Open. 2019;9(10):e028728.

Davidson AJ, Morton NS, Arnup SJ, de Graaf JC, Disma N, Withington DE, et al. Apnea after Awake Regional and General Anesthesia in infants: the General Anesthesia compared to spinal anesthesia study-comparing apnea and neurodevelopmental outcomes, a Randomized Controlled Trial. Anesthesiology. 2015;123(1):38–54.

Jones LJ, Craven PD, Lakkundi A, Foster JP, Badawi N. Regional (spinal, epidural, caudal) versus general anaesthesia in preterm infants undergo ing inguinal herniorrhaphy in early infancy. Cochrane Database Syst Rev. 2015;6:CD003669.

Whitaker EE, Williams RK. Epidural and spinal anesthesia for newborn surgery. Clin Perinatol. 2019;46(4):731–43. https://doi.org/10.1016/j.clp.2019.08.007 . Epub 2019 Aug 15.

Bosenberg AT, Johr M, Wolf AR. Pro con debate: the use of regional vs systemic analgesia for neonatal surgery. Paediatr Anaesth. 2011;21(12):1247–58.

Suresh S, Long J, Birmingham PK, et al. Are caudal blocks for pain control safe in children? An analysis of 18,650 caudal blocks from the Pediatric Regional Anesthesia Network (PRAN) database. Anesth Analg. 2015;120(1):151–6.

Tirotta CF, Alcos S, Lagueruela RG, et al. Three-year experience with immediate extubation in pediatric patients after congenital cardiac surgery. J Cardiothorac Surg. 2020;15(1):1.

Yu AL, Cai XZ, Gao XJ, et al. Determinants of immediate extubation in the operating room after total thoracoscopic closure of congenital heart defects. Med Princ Pract. 2013;22(3):234–8.

Parmar D, Lakhia K, Garg P, Patel K, Shah R, Surti J, Panchal J, Pandya H. Risk factors for delayed extubation after ventricular septal defect Closure: a prospective observational study. Braz J Cardiovasc Surg. 2017;32(4):276–82.

Mukerji A, Razak A, Aggarwal A, Jacobi E, Musa M, Alwahab Z, et al. Early versus delayed extubation in extremely preterm neonates: a retrospective cohort study. J Perinatol. 2020;40:118–23.

Download references

All phases of this study were supported by the Science & Technology Department of Sichuan Province (No. 2023NSFSC1626).

Author information

Qianqian Zhang and Jing Xu contributed equally to this research.

Authors and Affiliations

Department of Anesthesiology, The Affiliated Hospital, School of Medicine, UESTC Chengdu Women’s & Children’s Central Hospital, Chengdu, 610091, China

Qianqian Zhang, Jing Xu, Qinghua Huang, Tianqing Gong, Jia Li & Yu Cui

You can also search for this author in PubMed   Google Scholar

Contributions

Y.C, QZ and JX contributed to conceptualization, literature search, software, data analysis, writing of the original draft, reviewing and editing. QH, TG and JL contributed to data collection. All the authors approved the final version of the manuscript.

Corresponding author

Correspondence to Yu Cui .

Ethics declarations

Ethics approval and consent to participate.

This study was approved by the Institutional Review Board (IRB) of Chengdu Women’s and Children’s Central Hospital [No. 2022 (100)]. The need for Informed Consent was waived by the Institutional Review Board (IRB) of Chengdu Women’s and Children’s Central Hospital due to the retrospective nature of the study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Zhang, Q., Xu, J., Huang, Q. et al. Risk factors for delayed extubation after pediatric perineal anaplasty in patients less than 1 year of age: a retrospective study. BMC Pediatr 24 , 307 (2024). https://doi.org/10.1186/s12887-024-04781-4

Download citation

Received : 18 October 2023

Accepted : 22 April 2024

Published : 06 May 2024

DOI : https://doi.org/10.1186/s12887-024-04781-4

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Risk factors
• Delayed extubation
• Perineal angioplasty

BMC Pediatrics

ISSN: 1471-2431

• Submission enquiries: [email protected]
• General enquiries: [email protected]