What is a t-test?

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License http://creativecommons.org/licenses/b...

Transcript:
What is a t-test?

A t-test is used to find out if two sets of data are significantly different from each other. It compares the two sets of data and their means. You could use a t-test to determine if a difference in grades exists between children attending a private or public school.

The t-test was developed by William Sealy Gosset. He was an employee at the Guinness brewery which did not allow employees to publish research. Gosset was able to convince his employer his work was not a trade secret, and he was able to publish under the name “student”.

The t-test assumes the data follows a normal distribution and the variances of the two groups of data to be equal.

The test uses a null and alternative hypotheses. The null hypothesis states there is no difference between the groups. For example, the null hypothesis states that no difference exists in the grades between children attending a private or public school. The alternative or research hypothesis states a difference in grades between the two school systems exists.

The value resulting from a t-test is called the p-value. The value tells us how likely the difference between the two groups could have happened by accident. If the p-value is less than 0.05 then there is a statistically significant difference between the two groups.

A t-test is used to find out if a significant difference exists between two groups of data. Software is available which will allow you to run a t-test.

Need help? Ask us. Email, chat or drop by.

[Facebook: @McLaughlinLibrary
Snapchat/Instagram/Twitter: @UGLibrary]

[This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.]