T test in Excel

T test in Excel

In this video, we will show how you can perform a t-test using Excel. A t-test is a statistical tool in hypothesis testing to test the means of two groups of data when the variances are unknown.

0:00 T-test introduction 0:50 Defining the Problem for the T-test 1:09 Performing the T-test in Excel 1:30 How to choose the correct T-test to use 2:24 Entering the Excel parameters for the T-test 3: 32 T-test Output - Variable information 4:00 Difference between One- and Two-tailed Tests 4:41 P-values

https://softtechtutorials.com/microsoft-office/excel/t-test-in-excel/

We assume that the underlying distributions of the data sets are normal. However, when our sample sizes are large enough the shape of the sampling distributions will approach normality regardless of the variables’ underlying distributions. Under the null hypothesis, the test statistic follows a Student's t-distribution.

T-test in Excel – Setting the Scene On this sheet, we have 30 observations of the average resting heart rate of non-athletes and athletes. The question is whether or not there is a significant difference between these two.

Defining the Problem for the T-test To test this, we state our null hypothesis H_0 as the average heart rate of the athletes stated by mu_athletes equals the average heart rate of the non-athletes stated by mu_non-athletes. The alternative hypothesis is then mu_athletes is not equal to mu_non-athletes.

Performing the T-test in Excel To perform a t-test, we navigate to Data and select Data Analysis. A menu opens where we scroll down to the t-tests. We see that there are three different options to choose from: “t-Test:Paired Two Sample for Means”, “t-Test: Two-Sample Assuming Equal Variances”, and “t-Test: Two-Sample Assuming Unequal Variances”.

How to choose the correct T-test to use To determine which t-test to use, we look at whether or not there is a relationship between the datasets and we have to make the distinction based on the sample sizes and variances. When both groups of data are related, we select the first t-test.

The next case to distinguish is when we have equal or unequal sample sizes and similar variances. Then the test statistic is adjusted to take this into account. The final case is where we have equal or unequal sample sizes and unequal variances. In this case, Excel performs Welch’s test to find the correct t-statistic.

Entering the Excel parameters for the T-test Here, we have non-paired populations and variances that are significantly different from each other. We have tested this before using the F-test. So, we select “t-Test: Two-Sample Assuming Unequal Variances” .

A menu opens where we have to enter some data for testing. First, we need variable 1 range which is the non-athletes' ... https://www.youtube.com/watch?v=SQq0hJlug2w