ABSTRACT
When a subject is tested on the same variable over time, it is a repeated measures design. While the advantages of repeated measurements are obvious (e.g., they require fewer subjects per experiment, and they eliminate between-subjects differences from the experimental error), they violate the most important assumption of multivariate analysis, independencethe same subject is measured repeatedly on the same variable. GLM for repeated measures is a special procedure that can account for this dependence and still test for differences across individuals for the set of dependent variables.
