Code. Models. Analysis. Decisions.

Inferential Statistics with Minitab

Paired Samples Hypothesis Testing

This tutorial demonstrates how to use Minitab to conduct paired samples hypothesis tests. These tests are sometimes referred to as matched pairs test, related samples or repeated measures tests. This common form of the hypothesis test is used to determine whether any observed difference between some form of "before" and "after" scenario is merely random chance or statistically measurable (significant).

In this example we are pairing fictitious data about medical tests performed at two different hospitals. The assumption is that since these are the same tests conducted by similarly credentialed profrssionals that there should be no difference in the cost of the same procedure just because it is carried out at different locations.

This idea is represented by the null hypothesis. The alternative is that there is a differnce in cost.

The data used in the video can be downloaded here.

More Videos