Paired Data and Repeated Measures

Paired data occurs when there is a direct relationship between measures in the different groups.  An example would be specific students who took a pre-test and a post-test. The pre/post test score comparison would be a paired comparison because we have the same students in both groups.  If you randomly sample 50 test scores from Town A and 50 test scores form Town B, however, and compare the two towns, the data would be unpaired since there isn’t a link between the individual tests in the two groups.

When you have paired data, you benefit greatly from using tests for paired data that take advantage of this fact because it gives you much greater statistical power.  In effect, the variables pairings allow for the distributions

Repeated measures are a subtype of paired data in which the same measurement is repeated over time on the same subject variables (typically 3 more or more times).  Subjects who take a pre-test, a post-test, and a long-term post-test would be a repeated measures design.  Repeated lab tests on the same subjects are another example.