In a hypothetical study, I want to examine whether a new vocabulary learning app improves students’ test scores. I collect scores from the same group of 30 students before ...
In a hypothetical study, I want to examine whether a new vocabulary learning app improves students’ test scores. I collect scores from the same group of 30 students before using the app (pre-test) and again after four weeks (post-test). Because the data come from one group measured at two different times, the scores are naturally paired. For this reason, I would use a paired samples t-test. This test is appropriate when the two sets of scores come from the same participants, and we want to see whether there is a significant change within that group.
If I instead compared two different classes—one using the app and one not using it—then I would choose an independent samples t-test, because the groups would involve different participants and we would be comparing their mean scores. But for the original scenario with pre-test and post-test scores from the same students, the paired samples t-test is the correct choice.