Paired t-test

Last revised by Matt A. Morgan on 11 Aug 2015

The paired t-test is the appropriate method when the researcher takes an experimental group, measures the baseline, subjects the members to an intervention, and then measures the results.

Testing in a before-and-after manner like this ("matched data" or "repeated measures") requires a different statistical technique than the typical student t-test

t = d / (s / √n)
  • t: t-score
  • d: difference between the mean before and after
  • s: standard deviation
  • √n: √(number in the sample)

If the t is significant, then the null hypothesis (no difference between the groups) can be rejected. The degree of freedom of the test is (n/2-1); so effectively the sample number has to be doubled to acheive the same number of degrees of freedom as a typical student t-test.

It is important to remember when reading a study that a "one-tailed" test is less stringent than a "two-tailed" test.

ADVERTISEMENT: Supporters see fewer/no ads

Updating… Please wait.

 Unable to process the form. Check for errors and try again.

 Thank you for updating your details.