Assumptions in Repeated Measures ANOVA
Except for independence of samples, the assumptions for simple ANOVA, (between subjects
designs), discussed in chapter 9 also hold true for repeated measures ANOVA,
(within-subjects designs). But with repeated measures designs, we must also consider
the relationships among the repeated measures. Repeated measures ANOVA
must meet the assumption of sphericity, sometimes referred to as compound symmetry.
Sphericity requires that the repeated measures demonstrate homogeneity of
variance (see chapter 8, assumptions for the t test) and homogeneity of covariance.
Homogeneity of covariance means that the relationships, or correlations, on the
dependent variable among all of the three or more repeated measures are equal.
When only two repeated measures are ern ployed (such as pre-post measures for a t
test), this assumption is not applicable, because there is only one correlation coeffcient
that can be calculated, the correlation between pre- and post test scores. Methods
of dealing with violations of sphericity will be presented later in this chapter