null hypothesis in data science

Hypothesis Testing: Null Hypothesis and Alternative Hypothesis

Join over 2 million students who advanced their careers with 365 Data Science. Learn from instructors who have worked at Meta, Spotify, Google, IKEA, Netflix, and Coca-Cola and master Python, SQL, Excel, machine learning, data analysis, AI fundamentals, and more.

Figuring out exactly what the null hypothesis and the alternative hypotheses are is not a walk in the park. Hypothesis testing is based on the knowledge that you can acquire by going over what we have previously covered about statistics in our blog.

So, if you don’t want to have a hard time keeping up, make sure you have read all the tutorials about confidence intervals , distributions , z-tables and t-tables .

We've also made a video on null hypothesis vs alternative hypothesis - you can watch it below or just scroll down if you prefer reading.

Confidence intervals provide us with an estimation of where the parameters are located. You can obtain them with our confidence interval calculator and learn more about them in the related article.

However, when we are making a decision, we need a yes or no answer. The correct approach, in this case, is to use a test .

Here we will start learning about one of the fundamental tasks in statistics - hypothesis testing !

The Hypothesis Testing Process

  First off, let’s talk about data-driven decision-making. It consists of the following steps:

• First, we must formulate a hypothesis .
• After doing that, we have to find the right test for our hypothesis .
• Then, we execute the test.
• Finally, we make a decision based on the result.

Let’s start from the beginning.

What is a Hypothesis?

Though there are many ways to define it, the most intuitive must be:

“A hypothesis is an idea that can be tested.”

This is not the formal definition, but it explains the point very well.

So, if we say that apples in New York are expensive, this is an idea or a statement. However, it is not testable, until we have something to compare it with.

For instance, if we define expensive as: any price higher than $1.75 dollars per pound, then it immediately becomes a hypothesis .

What Cannot Be a Hypothesis?

An example may be: would the USA do better or worse under a Clinton administration, compared to a Trump administration? Statistically speaking, this is an idea , but there is no data to test it. Therefore, it cannot be a hypothesis of a statistical test.

Actually, it is more likely to be a topic of another discipline.

Conversely, in statistics, we may compare different US presidencies that have already been completed. For example, the Obama administration and the Bush administration, as we have data on both.

A Two-Sided Test

Alright, let’s get out of politics and get into hypotheses . Here’s a simple topic that CAN be tested.

According to Glassdoor (the popular salary information website), the mean data scientist salary in the US is 113,000 dollars.

So, we want to test if their estimate is correct.

The Null and Alternative Hypotheses

There are two hypotheses that are made: the null hypothesis , denoted H 0 , and the alternative hypothesis , denoted H 1 or H A .

The null hypothesis is the one to be tested and the alternative is everything else. In our example:

The null hypothesis would be: The mean data scientist salary is 113,000 dollars.

While the alternative : The mean data scientist salary is not 113,000 dollars.

Author's note: If you're interested in a data scientist career, check out our articles Data Scientist Career Path , 5 Business Basics for Data Scientists , Data Science Interview Questions , and 15 Data Science Consulting Companies Hiring Now .

An Example of a One-Sided Test

You can also form one-sided or one-tailed tests.

Say your friend, Paul, told you that he thinks data scientists earn more than 125,000 dollars per year. You doubt him, so you design a test to see who’s right.

The null hypothesis of this test would be: The mean data scientist salary is more than 125,000 dollars.

The alternative will cover everything else, thus: The mean data scientist salary is less than or equal to 125,000 dollars.

Important: The outcomes of tests refer to the population parameter rather than the sample statistic! So, the result that we get is for the population.

Important: Another crucial consideration is that, generally, the researcher is trying to reject the null hypothesis . Think about the null hypothesis as the status quo and the alternative as the change or innovation that challenges that status quo. In our example, Paul was representing the status quo, which we were challenging.

Let’s go over it once more. In statistics, the null hypothesis is the statement we are trying to reject. Therefore, the null hypothesis is the present state of affairs, while the alternative is our personal opinion.

Why Hypothesis Testing Works

Right now, you may be feeling a little puzzled. This is normal because this whole concept is counter-intuitive at the beginning. However, there is an extremely easy way to continue your journey of exploring it. By diving into the linked tutorial, you will find out why hypothesis testing actually works.

Interested in learning more? You can take your skills from good to great with our statistics course!

Try statistics course for free

Next Tutorial:  Hypothesis Testing: Significance Level and Rejection Region

World-Class

Data Science

Learn with instructors from:

Iliya Valchanov

Co-founder of 365 Data Science

Iliya is a finance graduate with a strong quantitative background who chose the exciting path of a startup entrepreneur. He demonstrated a formidable affinity for numbers during his childhood, winning more than 90 national and international awards and competitions through the years. Iliya started teaching at university, helping other students learn statistics and econometrics. Inspired by his first happy students, he co-founded 365 Data Science to continue spreading knowledge. He authored several of the program’s online courses in mathematics, statistics, machine learning, and deep learning.

We Think you'll also like

Statistics Tutorials

False Positive vs. False Negative: Type I and Type II Errors in Statistical Hypothesis Testing

Hypothesis Testing with Z-Test: Significance Level and Rejection Region

Calculating and Using Covariance and Linear Correlation Coefficient

Examples of Numerical and Categorical Variables

• Onsite training

3,000,000+ delegates

15,000+ clients

1,000+ locations

• KnowledgePass
• Log a ticket

01344203999 Available 24/7

Hypothesis Testing in Data Science: It's Usage and Types

Hypothesis Testing in Data Science is a crucial method for making informed decisions from data. This blog explores its essential usage in analysing trends and patterns, and the different types such as null, alternative, one-tailed, and two-tailed tests, providing a comprehensive understanding for both beginners and advanced practitioners.

Exclusive 40% OFF

Training Outcomes Within Your Budget!

We ensure quality, budget-alignment, and timely delivery by our expert instructors.

Share this Resource

• Advanced Data Science Certification
• Data Science and Blockchain Training
• Big Data Analysis
• Python Data Science Course
• Advanced Data Analytics Course

Table of Contents  

1) What is Hypothesis Testing in Data Science? 

2) Importance of Hypothesis Testing in Data Science 

3) Types of Hypothesis Testing 

4) Basic steps in Hypothesis Testing 

5) Real-world use cases of Hypothesis Testing 

6) Conclusion 

What is Hypothesis Testing in Data Science?  

Hypothesis Testing in Data Science is a statistical method used to assess the validity of assumptions or claims about a population based on sample data. It involves formulating two Hypotheses, the null Hypothesis (H0) and the alternative Hypothesis (Ha or H1), and then using statistical tests to find out if there is enough evidence to support the alternative Hypothesis.  

Hypothetical Testing is a critical tool for making data-driven decisions, evaluating the significance of observed effects or differences, and drawing meaningful conclusions from data, allowing Data Scientists to uncover patterns, relationships, and insights that inform various domains, from medicine to business and beyond. 

Unlock the power of data with our comprehensive Data Science & Analytics Training . Sign up now!  

Importance of Hypothesis Testing in Data Science  

The significance of Hypothesis Testing in Data Science cannot be overstated. It serves as the cornerstone of data-driven decision-making. By systematically testing Hypotheses, Data Scientists can: 

Objective decision-making 

Hypothesis Testing provides a structured and impartial method for making decisions based on data. In a world where biases can skew perceptions, Data Scientists rely on this method to ensure that their conclusions are grounded in empirical evidence, making their decisions more objective and trustworthy. 

Statistical rigour 

Data Scientists deal with large amounts of data, and Hypothesis Testing helps them make sense of it. It quantifies the significance of observed patterns, differences, or relationships. This statistical rigour is essential in distinguishing between mere coincidences and meaningful findings, reducing the likelihood of making decisions based on random chance. 

Resource allocation 

Resources, whether they are financial, human, or time-related, are often limited. Hypothesis Testing enables efficient resource allocation by guiding Data Scientists towards strategies or interventions that are statistically significant. This ensures that efforts are directed where they are most likely to yield valuable results. 

Risk management 

In domains like healthcare and finance, where lives and livelihoods are at stake, Hypothesis Testing is a critical tool for risk assessment. For instance, in drug development, Hypothesis Testing is used to determine the safety and efficiency of new treatments, helping mitigate potential risks to patients. 

Innovation and progress 

Hypothesis Testing fosters innovation by providing a systematic framework to evaluate new ideas, products, or strategies. It encourages a cycle of experimentation, feedback, and improvement, driving continuous progress and innovation. 

Strategic decision-making 

Organisations base their strategies on data-driven insights. Hypothesis Testing enables them to make informed decisions about market trends, customer behaviour, and product development. These decisions are grounded in empirical evidence, increasing the likelihood of success. 

Scientific integrity 

In scientific research, Hypothesis Testing is integral to maintaining the integrity of research findings. It ensures that conclusions are drawn from rigorous statistical analysis rather than conjecture. This is essential for advancing knowledge and building upon existing research. 

Regulatory compliance 

Many industries, such as pharmaceuticals and aviation, operate under strict regulatory frameworks. Hypothesis Testing is essential for demonstrating compliance with safety and quality standards. It provides the statistical evidence required to meet regulatory requirements. 

Supercharge your data skills with our Big Data and Analytics Training – register now!  

Types of Hypothesis Testing  

Hypothesis Testing can be seen in several different types. In total, we have five types of Hypothesis Testing. They are described below as follows: 

Alternative Hypothesis

The Alternative Hypothesis, denoted as Ha or H1, is the assertion or claim that researchers aim to support with their data analysis. It represents the opposite of the null Hypothesis (H0) and suggests that there is a significant effect, relationship, or difference in the population. In simpler terms, it's the statement that researchers hope to find evidence for during their analysis. For example, if you are testing a new drug's efficacy, the alternative Hypothesis might state that the drug has a measurable positive effect on patients' health. 

Null Hypothesis 

The Null Hypothesis, denoted as H0, is the default assumption in Hypothesis Testing. It posits that there is no significant effect, relationship, or difference in the population being studied. In other words, it represents the status quo or the absence of an effect. Researchers typically set out to challenge or disprove the Null Hypothesis by collecting and analysing data. Using the drug efficacy example again, the Null Hypothesis might state that the new drug has no effect on patients' health. 

Non-directional Hypothesis 

A Non-directional Hypothesis, also known as a two-tailed Hypothesis, is used when researchers are interested in whether there is any significant difference, effect, or relationship in either direction (positive or negative). This type of Hypothesis allows for the possibility of finding effects in both directions. For instance, in a study comparing the performance of two groups, a Non-directional Hypothesis would suggest that there is a significant difference between the groups, without specifying which group performs better. 

Directional Hypothesis 

A Directional Hypothesis, also called a one-tailed Hypothesis, is employed when researchers have a specific expectation about the direction of the effect, relationship, or difference they are investigating. In this case, the Hypothesis predicts an outcome in a particular direction—either positive or negative. For example, if you expect that a new teaching method will improve student test scores, a directional Hypothesis would state that the new method leads to higher test scores. 

Statistical Hypothesis 

A Statistical Hypothesis is a Hypothesis formulated in a way that it can be tested using statistical methods. It involves specific numerical values or parameters that can be measured or compared. Statistical Hypotheses are crucial for quantitative research and often involve means, proportions, variances, correlations, or other measurable quantities. These Hypotheses provide a precise framework for conducting statistical tests and drawing conclusions based on data analysis. 

Want to unlock the power of Big Data Analysis? Join our Big Data Analysis Course today!  

Basic steps in Hypothesis Testing  

Hypothesis Testing is a systematic approach used in statistics to make informed decisions based on data. It is a critical tool in Data Science, research, and many other fields where data analysis is employed. The following are the basic steps involved in Hypothesis Testing: 

1) Formulate Hypotheses 

The first step in Hypothesis Testing is to clearly define your research question and translate it into two mutually exclusive Hypotheses: 

a) Null Hypothesis (H0): This is the default assumption, often representing the status quo or the absence of an effect. It states that there is no significant difference, relationship, or effect in the population. 

b) Alternative Hypothesis (Ha or H1): This is the statement that contradicts the null Hypothesis. It suggests that there is a significant difference, relationship, or effect in the population. 

The formulation of these Hypotheses is crucial, as they serve as the foundation for your entire Hypothesis Testing process. 

2) Collect data 

With your Hypotheses in place, the next step is to gather relevant data through surveys, experiments, observations, or any other suitable method. The data collected should be representative of the population you are studying. The quality and quantity of data are essential factors in the success of your Hypothesis Testing. 

3) Choose a significance level (α) 

Before conducting the statistical test, you need to decide on the level of significance, denoted as α. The significance level represents the threshold for statistical significance and determines how confident you want to be in your results. A common choice is α = 0.05, which implies a 5% chance of making a Type I error (rejecting the null Hypothesis when it's true). You can choose a different α value based on the specific requirements of your analysis. 

4) Perform the test 

Based on the nature of your data and the Hypotheses you've formulated, select the appropriate statistical test. There are various tests available, including t-tests, chi-squared tests, ANOVA, regression analysis, and more. The chosen test should align with the type of data (e.g., continuous or categorical) and the research question (e.g., comparing means or testing for independence). 

Execute the selected statistical test on your data to obtain test statistics and p-values. The test statistics quantify the difference or effect you are investigating, while the p-value represents the probability of obtaining the observed results if the null Hypothesis were true. 

5) Analyse the results 

Once you have the test statistics and p-value, it's time to interpret the results. The primary focus is on the p-value: 

a) If the p-value is less than or equal to your chosen significance level (α), typically 0.05, you have evidence to reject the null Hypothesis. This shows that there is a significant difference, relationship, or effect in the population. 

b) If the p-value is more than α, you fail to reject the null Hypothesis, showing that there is insufficient evidence to support the alternative Hypothesis. 

6) Draw conclusions 

Based on the analysis of the p-value and the comparison to the significance level, you can draw conclusions about your research question: 

a) In case you reject the null Hypothesis, you can accept the alternative Hypothesis and make inferences based on the evidence provided by your data. 

b) In case you fail to reject the null Hypothesis, you do not accept the alternative Hypothesis, and you acknowledge that there is no significant evidence to support your claim. 

It's important to communicate your findings clearly, including the implications and limitations of your analysis. 

Real-world use cases of Hypothesis Testing  

The following are some of the real-world use cases of Hypothesis Testing. 

a) Medical research: Hypothesis Testing is crucial in determining the efficacy of new medications or treatments. For instance, in a clinical trial, researchers use Hypothesis Testing to assess whether a new drug is significantly more effective than a placebo in treating a particular condition. 

b) Marketing and advertising: Businesses employ Hypothesis Testing to evaluate the impact of marketing campaigns. A company may test whether a new advertising strategy leads to a significant increase in sales compared to the previous approach. 

c) Manufacturing and quality control: Manufacturing industries use Hypothesis Testing to ensure product quality. For example, in the automotive industry, Hypothesis Testing can be applied to test whether a new manufacturing process results in a significant reduction in defects. 

d) Education: In the field of education, Hypothesis Testing can be used to assess the effectiveness of teaching methods. Researchers may test whether a new teaching approach leads to statistically significant improvements in student performance. 

e) Finance and investment: Investment strategies are often evaluated using Hypothesis Testing. Investors may test whether a new investment strategy outperforms a benchmark index over a specified period.  

Conclusion 

To sum it up, Hypothesis Testing in Data Science is a powerful tool that enables Data Scientists to make evidence-based decisions and draw meaningful conclusions from data. Understanding the types, methods, and steps involved in Hypothesis Testing is essential for any Data Scientist. By rigorously applying Hypothesis Testing techniques, you can gain valuable insights and drive informed decision-making in various domains. 

Want to take your Data Science skills to the next level? Join our Big Data Analytics & Data Science Integration Course now!  

Frequently Asked Questions

Upcoming data, analytics & ai resources batches & dates.

Fri 5th Jul 2024

Fri 1st Nov 2024

Get A Quote

WHO WILL BE FUNDING THE COURSE?

My employer

By submitting your details you agree to be contacted in order to respond to your enquiry

• Business Analysis
• Lean Six Sigma Certification

Share this course

Our biggest spring sale.

We cannot process your enquiry without contacting you, please tick to confirm your consent to us for contacting you about your enquiry.

By submitting your details you agree to be contacted in order to respond to your enquiry.

We may not have the course you’re looking for. If you enquire or give us a call on 01344203999 and speak to our training experts, we may still be able to help with your training requirements.

Or select from our popular topics

• ITIL® Certification
• Scrum Certification
• Change Management Certification
• Business Analysis Courses
• Microsoft Azure Certification
• Microsoft Excel Courses
• Microsoft Project
• Explore more courses

Press esc to close

Fill out your  contact details  below and our training experts will be in touch.

Fill out your   contact details   below

Thank you for your enquiry!

One of our training experts will be in touch shortly to go over your training requirements.

Back to Course Information

Fill out your contact details below so we can get in touch with you regarding your training requirements.

* WHO WILL BE FUNDING THE COURSE?

Preferred Contact Method

No preference

Back to course information

Fill out your  training details  below

Fill out your training details below so we have a better idea of what your training requirements are.

HOW MANY DELEGATES NEED TRAINING?

HOW DO YOU WANT THE COURSE DELIVERED?

Online Instructor-led

Online Self-paced

WHEN WOULD YOU LIKE TO TAKE THIS COURSE?

Next 2 - 4 months

WHAT IS YOUR REASON FOR ENQUIRING?

Looking for some information

Looking for a discount

I want to book but have questions

One of our training experts will be in touch shortly to go overy your training requirements.

Your privacy & cookies!

Like many websites we use cookies. We care about your data and experience, so to give you the best possible experience using our site, we store a very limited amount of your data. Continuing to use this site or clicking “Accept & close” means that you agree to our use of cookies. Learn more about our privacy policy and cookie policy cookie policy .

We use cookies that are essential for our site to work. Please visit our cookie policy for more information. To accept all cookies click 'Accept & close'.

9   Hypothesis testing

In scientific studies, you’ll often see phrases like “the results are statistically significant”. This points to a technique called hypothesis testing, where we use p-values, a type of probability, to test our initial assumption or hypothesis.

In hypothesis testing, rather than providing an estimate of the parameter we’re studying, we provide a probability that serves as evidence supporting or contradicting a specific hypothesis. The hypothesis usually involves whether a parameter is different from a predetermined value (often 0).

Hypothesis testing is used when you can phrase your research question in terms of whether a parameter differs from this predetermined value. It’s applied in various fields, asking questions such as: Does a medication extend the lives of cancer patients? Does an increase in gun sales correlate with more gun violence? Does class size affect test scores?

Take, for instance, the previously used example with colored beads. We might not be concerned about the exact proportion of blue beads, but instead ask: Are there more blue beads than red ones? This could be rephrased as asking if the proportion of blue beads is more than 0.5.

The initial hypothesis that the parameter equals the predetermined value is called the “null hypothesis”. It’s popular because it allows us to focus on the data’s properties under this null scenario. Once data is collected, we estimate the parameter and calculate the p-value, which is the probability of the estimate being as extreme as observed if the null hypothesis is true. If the p-value is small, it indicates the null hypothesis is unlikely, providing evidence against it.

We will see more examples of hypothesis testing in Chapter 17 .

9.1 p-values

Suppose we take a random sample of \(N=100\) and we observe \(52\) blue beads, which gives us \(\bar{X} = 0.52\) . This seems to be pointing to the existence of more blue than red beads since 0.52 is larger than 0.5. However, we know there is chance involved in this process and we could get a 52 even when the actual \(p=0.5\) . We call the assumption that \(p = 0.5\) a null hypothesis . The null hypothesis is the skeptic’s hypothesis.

We have observed a random variable \(\bar{X} = 0.52\) , and the p-value is the answer to the question: How likely is it to see a value this large, when the null hypothesis is true? If the p-value is small enough, we reject the null hypothesis and say that the results are statistically significant .

The p-value of 0.05 as a threshold for statistical significance is conventionally used in many areas of research. A cutoff of 0.01 is also used to define highly significance . The choice of 0.05 is somewhat arbitrary and was popularized by the British statistician Ronald Fisher in the 1920s. We do not recommend using these cutoff without justification and recommend avoiding the phrase statistically significant .

To obtain a p-value for our example, we write:

\[\mbox{Pr}(\mid \bar{X} - 0.5 \mid > 0.02 ) \]

assuming the \(p=0.5\) . Under the null hypothesis we know that:

\[ \sqrt{N}\frac{\bar{X} - 0.5}{\sqrt{0.5(1-0.5)}} \]

is standard normal. We, therefore, can compute the probability above, which is the p-value.

\[\mbox{Pr}\left(\sqrt{N}\frac{\mid \bar{X} - 0.5\mid}{\sqrt{0.5(1-0.5)}} > \sqrt{N} \frac{0.02}{ \sqrt{0.5(1-0.5)}}\right)\]

In this case, there is actually a large chance of seeing 52 or larger under the null hypothesis.

Keep in mind that there is a close connection between p-values and confidence intervals. If a 95% confidence interval of the spread does not include 0, we know that the p-value must be smaller than 0.05.

To learn more about p-values, you can consult any statistics textbook. However, in general, we prefer reporting confidence intervals over p-values because it gives us an idea of the size of the estimate. If we just report the p-value, we provide no information about the significance of the finding in the context of the problem.

We can show mathematically that if a \((1-\alpha)\times 100\) % confidence interval does not contain the null hypothesis value, the null hypothesis is rejected with a p-value as smaller or smaller than \(\alpha\) . So statistical significance can be determined from confidence intervals. However, unlike the confidence interval, the p-value does not provide an estimate of the magnitude of the effect. For this reason, we recommend avoiding p-values whenever you can compute a confidence interval.

Pollsters are not successful at providing correct confidence intervals, but rather at predicting who will win. When we took a 25 bead sample size, the confidence interval for the spread:

included 0. If this were a poll and we were forced to make a declaration, we would have to say it was a “toss-up”.

One problem with our poll results is that, given the sample size and the value of \(p\) , we would have to sacrifice the probability of an incorrect call to create an interval that does not include 0.

This does not mean that the election is close. It only means that we have a small sample size. In statistical textbooks, this is called lack of power . In the context of polls, power is the probability of detecting spreads different from 0.

By increasing our sample size, we lower our standard error, and thus, have a much better chance of detecting the direction of the spread.

9.3 Exercises

• Generate a sample of size \(N=1000\) from an urn model with 50% blue beads:

then, compute a p-value to test if \(p=0.5\) . Repeat this 10,000 times and report how often the p-value is lower than 0.05? How often is it lower than 0.01?

• Make a histogram of the p-values you generated in exercise 1. Which of the following seems to be true?
• The p-values are all 0.05.
• The p-values are normally distributed; CLT seems to hold.
• The p-values are uniformly distributed.
• The p-values are all less than 0.05.

Demonstrate, mathematically, why see the histogram we see in exercise 2.

Generate a sample of size \(N=1000\) from an urn model with 52% blue beads:

Compute a p-value to test if \(p=0.5\) . Repeat this 10,000 times and report how often the p-value is larger than 0.05? Note that you are computing 1 - power.

• Repeat exercise for but for the following values:

Plot power as a function of \(N\) with a different color curve for each value of p .

For enquiries call:

+1-469-442-0620

• Data Science

Hypothesis Testing in Data Science [Types, Process, Example]

Home Blog Data Science Hypothesis Testing in Data Science [Types, Process, Example]

In day-to-day life, we come across a lot of data lot of variety of content. Sometimes the information is too much that we get confused about whether the information provided is correct or not. At that moment, we get introduced to a word called “Hypothesis testing” which helps in determining the proofs and pieces of evidence for some belief or information.  

What is Hypothesis Testing?

Hypothesis testing is an integral part of statistical inference. It is used to decide whether the given sample data from the population parameter satisfies the given hypothetical condition. So, it will predict and decide using several factors whether the predictions satisfy the conditions or not. In simpler terms, trying to prove whether the facts or statements are true or not.   

For example, if you predict that students who sit on the last bench are poorer and weaker than students sitting on 1st bench, then this is a hypothetical statement that needs to be clarified using different experiments. Another example we can see is implementing new business strategies to evaluate whether they will work for the business or not. All these things are very necessary when you work with data as a data scientist.  If you are interested in learning about data science, visit this amazing  Data Science full course   to learn data science.    

How is Hypothesis Testing Used in Data Science?

It is important to know how and where we can use hypothesis testing techniques in the field of data science. Data scientists predict a lot of things in their day-to-day work, and to check the probability of whether that finding is certain or not, we use hypothesis testing. The main goal of hypothesis testing is to gauge how well the predictions perform based on the sample data provided by the population. If you are interested to know more about the applications of the data, then refer to this  D ata  Scien ce course in India  which will give you more insights into application-based things. When data scientists work on model building using various machine learning algorithms, they need to have faith in their models and the forecasting of models. They then provide the sample data to the model for training purposes so that it can provide us with the significance of statistical data that will represent the entire population.  

Where and When to Use Hypothesis Test?

Hypothesis testing is widely used when we need to compare our results based on predictions. So, it will compare before and after results. For example, someone claimed that students writing exams from blue pen always get above 90%; now this statement proves it correct, and experiments need to be done. So, the data will be collected based on the student's input, and then the test will be done on the final result later after various experiments and observations on students' marks vs pen used, final conclusions will be made which will determine the results. Now hypothesis testing will be done to compare the 1st and the 2nd result, to see the difference and closeness of both outputs. This is how hypothesis testing is done.  

How Does Hypothesis Testing Work in Data Science?

In the whole data science life cycle, hypothesis testing is done in various stages, starting from the initial part, the 1st stage where the EDA, data pre-processing, and manipulation are done. In this stage, we will do our initial hypothesis testing to visualize the outcome in later stages. The next test will be done after we have built our model, once the model is ready and hypothesis testing is done, we will compare the results of the initial testing and the 2nd one to compare the results and significance of the results and to confirm the insights generated from the 1st cycle match with the 2nd one or not. This will help us know how the model responds to the sample training data. As we saw above, hypothesis testing is always needed when we are planning to contrast more than 2 groups. While checking on the results, it is important to check on the flexibility of the results for the sample and the population. Later, we can judge on the disagreement of the results are appropriate or vague. This is all we can do using hypothesis testing.   

Different Types of Hypothesis Testing

Hypothesis testing can be seen in several types. In total, we have 5 types of hypothesis testing. They are described below:

1. Alternative Hypothesis

The alternative hypothesis explains and defines the relationship between two variables. It simply indicates a positive relationship between two variables which means they do have a statistical bond. It indicates that the sample observed is going to influence or affect the outcome. An alternative hypothesis is described using H a  or H 1 . Ha indicates an alternative hypothesis and H 1  explains the possibility of influenced outcome which is 1. For example, children who study from the beginning of the class have fewer chances to fail. An alternate hypothesis will be accepted once the statistical predictions become significant. The alternative hypothesis can be further divided into 3 parts.   

• Left-tailed: Left tailed hypothesis can be expected when the sample value is less than the true value.   
• Right-tailed: Right-tailed hypothesis can be expected when the true value is greater than the outcome/predicted value.    
• Two-tailed: Two-tailed hypothesis is defined when the true value is not equal to the sample value or the output.   

2. Null Hypothesis

The null hypothesis simply states that there is no relation between statistical variables. If the facts presented at the start do not match with the outcomes, then we can say, the testing is null hypothesis testing. The null hypothesis is represented as H 0 . For example, children who study from the beginning of the class have no fewer chances to fail. There are types of Null Hypothesis described below:   

Simple Hypothesis:  It helps in denoting and indicating the distribution of the population.   

Composite Hypothesis:  It does not denote the population distribution   

Exact Hypothesis:  In the exact hypothesis, the value of the hypothesis is the same as the sample distribution. Example- μ= 10   

Inexact Hypothesis:  Here, the hypothesis values are not equal to the sample. It will denote a particular range of values.   

3. Non-directional Hypothesis 

The non-directional hypothesis is a tow-tailed hypothesis that indicates the true value does not equal the predicted value. In simpler terms, there is no direction between the 2 variables. For an example of a non-directional hypothesis, girls and boys have different methodologies to solve a problem. Here the example explains that the thinking methodologies of a girl and a boy is different, they don’t think alike.    

4. Directional Hypothesis

In the Directional hypothesis, there is a direct relationship between two variables. Here any of the variables influence the other.   

5. Statistical Hypothesis

Statistical hypothesis helps in understanding the nature and character of the population. It is a great method to decide whether the values and the data we have with us satisfy the given hypothesis or not. It helps us in making different probabilistic and certain statements to predict the outcome of the population... We have several types of tests which are the T-test, Z-test, and Anova tests.  

Methods of Hypothesis Testing

1. frequentist hypothesis testing.

Frequentist hypotheses mostly work with the approach of making predictions and assumptions based on the current data which is real-time data. All the facts are based on current data. The most famous kind of frequentist approach is null hypothesis testing.    

2. Bayesian Hypothesis Testing

Bayesian testing is a modern and latest way of hypothesis testing. It is known to be the test that works with past data to predict the future possibilities of the hypothesis. In Bayesian, it refers to the prior distribution or prior probability samples for the observed data. In the medical Industry, we observe that Doctors deal with patients’ diseases using past historical records. So, with this kind of record, it is helpful for them to understand and predict the current and upcoming health conditions of the patient.

Importance of Hypothesis Testing in Data Science

Most of the time, people assume that data science is all about applying machine learning algorithms and getting results, that is true but in addition to the fact that to work in the data science field, one needs to be well versed with statistics as most of the background work in Data science is done through statistics. When we deal with data for pre-processing, manipulating, and analyzing, statistics play. Specifically speaking Hypothesis testing helps in making confident decisions, predicting the correct outcomes, and finding insightful conclusions regarding the population. Hypothesis testing helps us resolve tough things easily. To get more familiar with Hypothesis testing and other prediction models attend the superb useful  KnowledgeHut Data Science full course  which will give you more domain knowledge and will assist you in working with industry-related projects.          

Basic Steps in Hypothesis Testing [Workflow]

1. null and alternative hypothesis.

After we have done our initial research about the predictions that we want to find out if true, it is important to mention whether the hypothesis done is a null hypothesis(H0) or an alternative hypothesis (Ha). Once we understand the type of hypothesis, it will be easy for us to do mathematical research on it. A null hypothesis will usually indicate the no-relationship between the variables whereas an alternative hypothesis describes the relationship between 2 variables.    

• H0 – Girls, on average, are not strong as boys   
• Ha - Girls, on average are stronger than boys   

2. Data Collection

To prove our statistical test validity, it is essential and critical to check the data and proceed with sampling them to get the correct hypothesis results. If the target data is not prepared and ready, it will become difficult to make the predictions or the statistical inference on the population that we are planning to make. It is important to prepare efficient data, so that hypothesis findings can be easy to predict.   

3. Selection of an appropriate test statistic

To perform various analyses on the data, we need to choose a statistical test. There are various types of statistical tests available. Based on the wide spread of the data that is variance within the group or how different the data category is from one another that is variance without a group, we can proceed with our further research study.   

4. Selection of the appropriate significant level

Once we get the result and outcome of the statistical test, we have to then proceed further to decide whether the reject or accept the null hypothesis. The significance level is indicated by alpha (α). It describes the probability of rejecting or accepting the null hypothesis. Example- Suppose the value of the significance level which is alpha is 0.05. Now, this value indicates the difference from the null hypothesis. 

5. Calculation of the test statistics and the p-value

P value is simply the probability value and expected determined outcome which is at least as extreme and close as observed results of a hypothetical test. It helps in evaluating and verifying hypotheses against the sample data. This happens while assuming the null hypothesis is true. The lower the value of P, the higher and better will be the results of the significant value which is alpha (α). For example, if the P-value is 0.05 or even less than this, then it will be considered statistically significant. The main thing is these values are predicted based on the calculations done by deviating the values between the observed one and referenced one. The greater the difference between values, the lower the p-value will be.

6. Findings of the test

After knowing the P-value and statistical significance, we can determine our results and take the appropriate decision of whether to accept or reject the null hypothesis based on the facts and statistics presented to us.

How to Calculate Hypothesis Testing?

Hypothesis testing can be done using various statistical tests. One is Z-test. The formula for Z-test is given below:  

            Z = ( x̅  – μ 0 )  / (σ /√n)    

In the above equation, x̅ is the sample mean   

• μ0 is the population mean   
• σ is the standard deviation    
• n is the sample size   

Now depending on the Z-test result, the examination will be processed further. The result is either going to be a null hypothesis or it is going to be an alternative hypothesis. That can be measured through below formula-   

• H0: μ=μ0   
• Ha: μ≠μ0   
• Here,   
• H0 = null hypothesis   
• Ha = alternate hypothesis   

In this way, we calculate the hypothesis testing and can apply it to real-world scenarios.

Real-World Examples of Hypothesis Testing

Hypothesis testing has a wide variety of use cases that proves to be beneficial for various industries.    

1. Healthcare

In the healthcare industry, all the research and experiments which are done to predict the success of any medicine or drug are done successfully with the help of Hypothesis testing.   

2. Education sector

Hypothesis testing assists in experimenting with different teaching techniques to deal with the understanding capability of different students.   

3. Mental Health

Hypothesis testing helps in indicating the factors that may cause some serious mental health issues.   

4. Manufacturing

Testing whether the new change in the process of manufacturing helped in the improvement of the process as well as in the quantity or not.  In the same way, there are many other use cases that we get to see in different sectors for hypothesis testing. 

Error Terms in Hypothesis Testing

1. type-i error.

Type I error occurs during the process of hypothesis testing when the null hypothesis is rejected even though it is accurate. This kind of error is also known as False positive because even though the statement is positive or correct but results are given as false. For example, an innocent person still goes to jail because he is considered to be guilty.   

2. Type-II error

Type II error occurs during the process of hypothesis testing when the null hypothesis is not rejected even though it is inaccurate. This Kind of error is also called a False-negative which means even though the statements are false and inaccurate, it still says it is correct and doesn’t reject it. For example, a person is guilty, but in court, he has been proven innocent where he is guilty, so this is a Type II error.   

3. Level of Significance

The level of significance is majorly used to measure the confidence with which a null hypothesis can be rejected. It is the value with which one can reject the null hypothesis which is H0. The level of significance gauges whether the hypothesis testing is significant or not.   

P-value stands for probability value, which tells us the probability or likelihood to find the set of observations when the null hypothesis is true using statistical tests. The main purpose is to check the significance of the statistical statement.   

5. High P-Values

A higher P-value indicates that the testing is not statistically significant. For example, a P value greater than 0.05 is considered to be having higher P value. A higher P-value also means that our evidence and proofs are not strong enough to influence the population.

In hypothesis testing, each step is responsible for getting the outcomes and the results, whether it is the selection of statistical tests or working on data, each step contributes towards the better consequences of the hypothesis testing. It is always a recommendable step when planning for predicting the outcomes and trying to experiment with the sample; hypothesis testing is a useful concept to apply.   

Frequently Asked Questions (FAQs)

We can test a hypothesis by selecting a correct hypothetical test and, based on those getting results.   

Many statistical tests are used for hypothetical testing which includes Z-test, T-test, etc. 

Hypothesis helps us in doing various experiments and working on a specific research topic to predict the results.   

The null and alternative hypothesis, data collection, selecting a statistical test, selecting significance value, calculating p-value, check your findings.    

In simple words, parametric tests are purely based on assumptions whereas non-parametric tests are based on data that is collected and acquired from a sample.   

Gauri Guglani

Gauri Guglani works as a Data Analyst at Deloitte Consulting. She has done her major in Information Technology and holds great interest in the field of data science. She owns her technical skills as well as managerial skills and also is great at communicating. Since her undergraduate, Gauri has developed a profound interest in writing content and sharing her knowledge through the manual means of blog/article writing. She loves writing on topics affiliated with Statistics, Python Libraries, Machine Learning, Natural Language processes, and many more.

Avail your free 1:1 mentorship session.

Something went wrong

Upcoming Data Science Batches & Dates

What Is a Null Hypothesis?

A null hypothesis may be a sort of hypothesis utilized in statistics that proposes that there’s no difference between certain characteristics of a population (or data-generating process). For example, a gambler could also be curious about whether a game of chance is fair. If it’s fair, then the expected earnings per play is 0 for […]

A null hypothesis may be a sort of hypothesis utilized in statistics that proposes that there’s no difference between certain characteristics of a population (or data-generating process).

For example, a gambler could also be curious about whether a game of chance is fair. If it’s fair, then the expected earnings per play is 0 for both players. If the sport isn’t fair, then the expected earnings are positive for one player and negative for the opposite. to check whether the sport is fair, the gambler collects earnings data from many repetitions of the sport , calculates the typical earnings from these data, then tests the null hypothesis that the expected earnings isn’t different from zero.

If the typical earnings from the sample data is sufficiently faraway from zero, then the gambler will reject the null hypothesis and conclude the choice hypothesis; namely, that the expected earnings per play is different from zero. If the typical earnings from the sample data are on the brink of zero, then the gambler won’t reject the null hypothesis, concluding instead that the difference between the typical from the info and 0 is explainable accidentally alone.

KEY TAKEAWAYS

A null hypothesis may be a sort of conjecture utilized in statistics that proposes that there’s no difference between certain characteristics of a population or data-generating process.

The alternative hypothesis proposes that there’s a difference.

Hypothesis testing provides a way to reject a null hypothesis within a particular confidence level. (Null hypotheses can’t be proven, though.)

How a Null Hypothesis Works

The null hypothesis, also referred to as the conjecture, assumes that any quite difference between the chosen characteristics that you simply see during a set of knowledge is thanks to chance. For instance, if the expected earnings for the game of chance are actually adequate to 0, then any difference between the typical earnings within the data and 0 is thanks to chance.

Statistical hypotheses are tested employing a four-step process. The primary step is for the analyst to state the 2 hypotheses in order that just one is often right. Subsequent step is to formulate an analysis plan, which outlines how the info is going to be evaluated. The third step is to hold out the plan and physically analyze the sample data. The fourth and final step is to research the results and either reject the null hypothesis, or claim that the observed differences are explainable accidentally alone.

Analysts look to reject the null hypothesis because it’s a robust conclusion. The choice conclusion, that the results are “explainable accidentally alone,” could also be a weak conclusion because it allows that factors aside from chance may be at work.

Analysts look to reject the null hypothesis to rule out some variable(s) as explaining the phenomena of interest.

Null Hypothesis Example

Here may be a simple example: a faculty principal reports that students in her school score a mean of seven out of 10 in exams. The null hypothesis is that the population mean is 7.0. To check this null hypothesis, we record marks of say 30 students (sample) from the whole student population of the varsity (say 300) and calculate the mean of that sample. We will then compare the (calculated) sample mean to the (claimed) population mean of seven .0 and plan to reject the null hypothesis. (The null hypothesis that the population mean is 7.0 can’t be proven using the sample data; it can only be rejected.)

Take another example: The annual return of a specific open-end fund is claimed to be 8%. Assume that open-end fund has been alive for 20 years. The null hypothesis is that the mean return is 8% for the open-end fund. We take a random sample of annual returns of the open-end fund for, say, five years (sample) and calculate the sample mean. We then compare the (calculated) sample mean to the (claimed) population mean (8%) to test the null hypothesis.

For the above examples, null hypotheses are:

Example A: Students within the school score a mean of seven out of 10 in exams.

Example B: Mean annual return of the open-end fund is 8% once a year.

For the needs of determining whether to reject the null hypothesis, the null hypothesis (abbreviated H0) is assumed, for the sake of argument, to be true. Then the likely range of possible values of the calculated statistic (e.g., average score on 30 students’ tests) is decided under this presumption (e.g., the range of plausible averages may range from 6.2 to 7.8 if the population mean is 7.0). Then, if the sample average is outside of this range, the null hypothesis is rejected. Otherwise, the difference is claimed to be “explainable accidentally alone,” being within the range that’s determined accidentally alone.

An important point to notice is that we are testing the null hypothesis because there’s a component of doubt about its validity. Whatever information that’s against the stated null hypothesis is captured within the Alternative Hypothesis (H1). For the above examples, the choice hypothesis would be:

Students score a mean that’s not adequate to 7.

The mean annual return of the open-end fund isn’t adequate to 8% once a year.

In other words, the choice hypothesis may be a direct contradiction of the null hypothesis.

Hypothesis Testing for Investments

As an example associated with financial markets, assume Alice sees that her investment strategy produces higher average returns than simply buying and holding a stock. The null hypothesis states that there’s no difference between the 2 average returns, and Alice is inclined to believe this until she proves otherwise. Refuting the null hypothesis would require showing statistical significance, which may be found employing a sort of tests. The choice hypothesis would state that the investment strategy features a higher average return than a standard buy-and-hold strategy.

The p-value is employed to work out the statistical significance of the results. A p-value that’s but or adequate to 0.05 is usually wont to indicate whether there’s evidence against the null hypothesis. If Alice conducts one among these tests, like a test using the traditional model, and proves that the difference between her returns and therefore the buy-and-hold returns is critical (p-value is a smaller amount than or adequate to 0.05), she will then refute the null hypothesis and conclude the choice hypothesis.

Weekly newsletter

No spam. Just the latest releases and tips, interesting articles, and exclusive interviews in your inbox every week.

You may also like

False negative.

While understanding the hypothesis, two errors can be quite confusing. These two errors are false negative and false positive. You can also refer to the false-negative error as type II error and false-positive as type I error. While you are learning, you might think these errors have no use and will only waste your time […]

Box Plot Review

A box plot or box and whisker plot help you display the database distribution on a five-number summary. The first quartile Q1 will be the minimum, the third quartile Q3 will be the median, and the fifth quartile Q5 will be the maximum. You can find the outliers and their values by using a box […]

Bayesian Networks

Creating a probabilistic model can be challenging but proves helpful in machine learning. To create such a graphical model, you need to find the probabilistic relationships between variables. Suppose you are creating a graphical representation of the variables. You need to represent the variables as nodes and conditional independence as the absence of edges. Graphical […]

Privacy Overview

• school Campus Bookshelves
• menu_book Bookshelves
• perm_media Learning Objects
• login Login
• how_to_reg Request Instructor Account
• hub Instructor Commons
• Download Page (PDF)
• Download Full Book (PDF)
• Periodic Table
• Physics Constants
• Scientific Calculator
• Reference & Cite
• Tools expand_more
• Readability

selected template will load here

This action is not available.

9.1: Null and Alternative Hypotheses

• Last updated
• Save as PDF
• Page ID 23459

The actual test begins by considering two hypotheses . They are called the null hypothesis and the alternative hypothesis . These hypotheses contain opposing viewpoints.

\(H_0\): The null hypothesis: It is a statement of no difference between the variables—they are not related. This can often be considered the status quo and as a result if you cannot accept the null it requires some action.

\(H_a\): The alternative hypothesis: It is a claim about the population that is contradictory to \(H_0\) and what we conclude when we reject \(H_0\). This is usually what the researcher is trying to prove.

Since the null and alternative hypotheses are contradictory, you must examine evidence to decide if you have enough evidence to reject the null hypothesis or not. The evidence is in the form of sample data.

After you have determined which hypothesis the sample supports, you make a decision. There are two options for a decision. They are "reject \(H_0\)" if the sample information favors the alternative hypothesis or "do not reject \(H_0\)" or "decline to reject \(H_0\)" if the sample information is insufficient to reject the null hypothesis.

\(H_{0}\) always has a symbol with an equal in it. \(H_{a}\) never has a symbol with an equal in it. The choice of symbol depends on the wording of the hypothesis test. However, be aware that many researchers (including one of the co-authors in research work) use = in the null hypothesis, even with > or < as the symbol in the alternative hypothesis. This practice is acceptable because we only make the decision to reject or not reject the null hypothesis.

Example \(\PageIndex{1}\)

• \(H_{0}\): No more than 30% of the registered voters in Santa Clara County voted in the primary election. \(p \leq 30\)
• \(H_{a}\): More than 30% of the registered voters in Santa Clara County voted in the primary election. \(p > 30\)

Exercise \(\PageIndex{1}\)

A medical trial is conducted to test whether or not a new medicine reduces cholesterol by 25%. State the null and alternative hypotheses.

• \(H_{0}\): The drug reduces cholesterol by 25%. \(p = 0.25\)
• \(H_{a}\): The drug does not reduce cholesterol by 25%. \(p \neq 0.25\)

Example \(\PageIndex{2}\)

We want to test whether the mean GPA of students in American colleges is different from 2.0 (out of 4.0). The null and alternative hypotheses are:

• \(H_{0}: \mu = 2.0\)
• \(H_{a}: \mu \neq 2.0\)

Exercise \(\PageIndex{2}\)

We want to test whether the mean height of eighth graders is 66 inches. State the null and alternative hypotheses. Fill in the correct symbol \((=, \neq, \geq, <, \leq, >)\) for the null and alternative hypotheses.

• \(H_{0}: \mu \_ 66\)
• \(H_{a}: \mu \_ 66\)
• \(H_{0}: \mu = 66\)
• \(H_{a}: \mu \neq 66\)

Example \(\PageIndex{3}\)

We want to test if college students take less than five years to graduate from college, on the average. The null and alternative hypotheses are:

• \(H_{0}: \mu \geq 5\)
• \(H_{a}: \mu < 5\)

Exercise \(\PageIndex{3}\)

We want to test if it takes fewer than 45 minutes to teach a lesson plan. State the null and alternative hypotheses. Fill in the correct symbol ( =, ≠, ≥, <, ≤, >) for the null and alternative hypotheses.

• \(H_{0}: \mu \_ 45\)
• \(H_{a}: \mu \_ 45\)
• \(H_{0}: \mu \geq 45\)
• \(H_{a}: \mu < 45\)

Example \(\PageIndex{4}\)

In an issue of U. S. News and World Report , an article on school standards stated that about half of all students in France, Germany, and Israel take advanced placement exams and a third pass. The same article stated that 6.6% of U.S. students take advanced placement exams and 4.4% pass. Test if the percentage of U.S. students who take advanced placement exams is more than 6.6%. State the null and alternative hypotheses.

• \(H_{0}: p \leq 0.066\)
• \(H_{a}: p > 0.066\)

Exercise \(\PageIndex{4}\)

On a state driver’s test, about 40% pass the test on the first try. We want to test if more than 40% pass on the first try. Fill in the correct symbol (\(=, \neq, \geq, <, \leq, >\)) for the null and alternative hypotheses.

• \(H_{0}: p \_ 0.40\)
• \(H_{a}: p \_ 0.40\)
• \(H_{0}: p = 0.40\)
• \(H_{a}: p > 0.40\)

COLLABORATIVE EXERCISE

Bring to class a newspaper, some news magazines, and some Internet articles . In groups, find articles from which your group can write null and alternative hypotheses. Discuss your hypotheses with the rest of the class.

In a hypothesis test , sample data is evaluated in order to arrive at a decision about some type of claim. If certain conditions about the sample are satisfied, then the claim can be evaluated for a population. In a hypothesis test, we:

• Evaluate the null hypothesis , typically denoted with \(H_{0}\). The null is not rejected unless the hypothesis test shows otherwise. The null statement must always contain some form of equality \((=, \leq \text{or} \geq)\)
• Always write the alternative hypothesis , typically denoted with \(H_{a}\) or \(H_{1}\), using less than, greater than, or not equals symbols, i.e., \((\neq, >, \text{or} <)\).
• If we reject the null hypothesis, then we can assume there is enough evidence to support the alternative hypothesis.
• Never state that a claim is proven true or false. Keep in mind the underlying fact that hypothesis testing is based on probability laws; therefore, we can talk only in terms of non-absolute certainties.

Formula Review

\(H_{0}\) and \(H_{a}\) are contradictory.

• If \(\alpha \leq p\)-value, then do not reject \(H_{0}\).
• If\(\alpha > p\)-value, then reject \(H_{0}\).

\(\alpha\) is preconceived. Its value is set before the hypothesis test starts. The \(p\)-value is calculated from the data.References

Data from the National Institute of Mental Health. Available online at http://www.nimh.nih.gov/publicat/depression.cfm .

9.1 Null and Alternative Hypotheses

The actual test begins by considering two hypotheses . They are called the null hypothesis and the alternative hypothesis . These hypotheses contain opposing viewpoints.

H 0 , the — null hypothesis: a statement of no difference between sample means or proportions or no difference between a sample mean or proportion and a population mean or proportion. In other words, the difference equals 0.

H a —, the alternative hypothesis: a claim about the population that is contradictory to H 0 and what we conclude when we reject H 0 .

Since the null and alternative hypotheses are contradictory, you must examine evidence to decide if you have enough evidence to reject the null hypothesis or not. The evidence is in the form of sample data.

After you have determined which hypothesis the sample supports, you make a decision. There are two options for a decision. They are reject H 0 if the sample information favors the alternative hypothesis or do not reject H 0 or decline to reject H 0 if the sample information is insufficient to reject the null hypothesis.

Mathematical Symbols Used in H 0 and H a :

H 0 always has a symbol with an equal in it. H a never has a symbol with an equal in it. The choice of symbol depends on the wording of the hypothesis test. However, be aware that many researchers use = in the null hypothesis, even with > or < as the symbol in the alternative hypothesis. This practice is acceptable because we only make the decision to reject or not reject the null hypothesis.

Example 9.1

H 0 : No more than 30 percent of the registered voters in Santa Clara County voted in the primary election. p ≤ 30 H a : More than 30 percent of the registered voters in Santa Clara County voted in the primary election. p > 30

A medical trial is conducted to test whether or not a new medicine reduces cholesterol by 25 percent. State the null and alternative hypotheses.

Example 9.2

We want to test whether the mean GPA of students in American colleges is different from 2.0 (out of 4.0). The null and alternative hypotheses are the following: H 0 : μ = 2.0 H a : μ ≠ 2.0

We want to test whether the mean height of eighth graders is 66 inches. State the null and alternative hypotheses. Fill in the correct symbol (=, ≠, ≥, <, ≤, >) for the null and alternative hypotheses.

• H 0 : μ __ 66
• H a : μ __ 66

Example 9.3

We want to test if college students take fewer than five years to graduate from college, on the average. The null and alternative hypotheses are the following: H 0 : μ ≥ 5 H a : μ < 5

We want to test if it takes fewer than 45 minutes to teach a lesson plan. State the null and alternative hypotheses. Fill in the correct symbol ( =, ≠, ≥, <, ≤, >) for the null and alternative hypotheses.

• H 0 : μ __ 45
• H a : μ __ 45

Example 9.4

An article on school standards stated that about half of all students in France, Germany, and Israel take advanced placement exams and a third of the students pass. The same article stated that 6.6 percent of U.S. students take advanced placement exams and 4.4 percent pass. Test if the percentage of U.S. students who take advanced placement exams is more than 6.6 percent. State the null and alternative hypotheses. H 0 : p ≤ 0.066 H a : p > 0.066

On a state driver’s test, about 40 percent pass the test on the first try. We want to test if more than 40 percent pass on the first try. Fill in the correct symbol (=, ≠, ≥, <, ≤, >) for the null and alternative hypotheses.

• H 0 : p __ 0.40
• H a : p __ 0.40

Collaborative Exercise

Bring to class a newspaper, some news magazines, and some internet articles. In groups, find articles from which your group can write null and alternative hypotheses. Discuss your hypotheses with the rest of the class.

As an Amazon Associate we earn from qualifying purchases.

This book may not be used in the training of large language models or otherwise be ingested into large language models or generative AI offerings without OpenStax's permission.

Want to cite, share, or modify this book? This book uses the Creative Commons Attribution License and you must attribute Texas Education Agency (TEA). The original material is available at: https://www.texasgateway.org/book/tea-statistics . Changes were made to the original material, including updates to art, structure, and other content updates.

Access for free at https://openstax.org/books/statistics/pages/1-introduction

• Authors: Barbara Illowsky, Susan Dean
• Publisher/website: OpenStax
• Book title: Statistics
• Publication date: Mar 27, 2020
• Location: Houston, Texas
• Book URL: https://openstax.org/books/statistics/pages/1-introduction
• Section URL: https://openstax.org/books/statistics/pages/9-1-null-and-alternative-hypotheses

© Jan 23, 2024 Texas Education Agency (TEA). The OpenStax name, OpenStax logo, OpenStax book covers, OpenStax CNX name, and OpenStax CNX logo are not subject to the Creative Commons license and may not be reproduced without the prior and express written consent of Rice University.

Statistics Made Easy

How to Write a Null Hypothesis (5 Examples)

A hypothesis test uses sample data to determine whether or not some claim about a population parameter is true.

Whenever we perform a hypothesis test, we always write a null hypothesis and an alternative hypothesis, which take the following forms:

H 0 (Null Hypothesis): Population parameter =,  ≤, ≥ some value

H A  (Alternative Hypothesis): Population parameter <, >, ≠ some value

Note that the null hypothesis always contains the equal sign .

We interpret the hypotheses as follows:

Null hypothesis: The sample data provides no evidence to support some claim being made by an individual.

Alternative hypothesis: The sample data  does provide sufficient evidence to support the claim being made by an individual.

For example, suppose it’s assumed that the average height of a certain species of plant is 20 inches tall. However, one botanist claims the true average height is greater than 20 inches.

To test this claim, she may go out and collect a random sample of plants. She can then use this sample data to perform a hypothesis test using the following two hypotheses:

H 0 : μ ≤ 20 (the true mean height of plants is equal to or even less than 20 inches)

H A : μ > 20 (the true mean height of plants is greater than 20 inches)

If the sample data gathered by the botanist shows that the mean height of this species of plants is significantly greater than 20 inches, she can reject the null hypothesis and conclude that the mean height is greater than 20 inches.

Read through the following examples to gain a better understanding of how to write a null hypothesis in different situations.

Example 1: Weight of Turtles

A biologist wants to test whether or not the true mean weight of a certain species of turtles is 300 pounds. To test this, he goes out and measures the weight of a random sample of 40 turtles.

Here is how to write the null and alternative hypotheses for this scenario:

H 0 : μ = 300 (the true mean weight is equal to 300 pounds)

H A : μ ≠ 300 (the true mean weight is not equal to 300 pounds)

Example 2: Height of Males

It’s assumed that the mean height of males in a certain city is 68 inches. However, an independent researcher believes the true mean height is greater than 68 inches. To test this, he goes out and collects the height of 50 males in the city.

H 0 : μ ≤ 68 (the true mean height is equal to or even less than 68 inches)

H A : μ > 68 (the true mean height is greater than 68 inches)

Example 3: Graduation Rates

A university states that 80% of all students graduate on time. However, an independent researcher believes that less than 80% of all students graduate on time. To test this, she collects data on the proportion of students who graduated on time last year at the university.

H 0 : p ≥ 0.80 (the true proportion of students who graduate on time is 80% or higher)

H A : μ < 0.80 (the true proportion of students who graduate on time is less than 80%)

Example 4: Burger Weights

A food researcher wants to test whether or not the true mean weight of a burger at a certain restaurant is 7 ounces. To test this, he goes out and measures the weight of a random sample of 20 burgers from this restaurant.

H 0 : μ = 7 (the true mean weight is equal to 7 ounces)

H A : μ ≠ 7 (the true mean weight is not equal to 7 ounces)

Example 5: Citizen Support

A politician claims that less than 30% of citizens in a certain town support a certain law. To test this, he goes out and surveys 200 citizens on whether or not they support the law.

H 0 : p ≥ .30 (the true proportion of citizens who support the law is greater than or equal to 30%)

H A : μ < 0.30 (the true proportion of citizens who support the law is less than 30%)

Additional Resources

Introduction to Hypothesis Testing Introduction to Confidence Intervals An Explanation of P-Values and Statistical Significance

Featured Posts

Hey there. My name is Zach Bobbitt. I have a Masters of Science degree in Applied Statistics and I’ve worked on machine learning algorithms for professional businesses in both healthcare and retail. I’m passionate about statistics, machine learning, and data visualization and I created Statology to be a resource for both students and teachers alike.  My goal with this site is to help you learn statistics through using simple terms, plenty of real-world examples, and helpful illustrations.

2 Replies to “How to Write a Null Hypothesis (5 Examples)”

you are amazing, thank you so much

Say I am a botanist hypothesizing the average height of daisies is 20 inches, or not? Does T = (ave – 20 inches) / √ variance / (80 / 4)? … This assumes 40 real measures + 40 fake = 80 n, but that seems questionable. Please advise.

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *