Answers are grounded in this paper and cite their sources.
Repeated measurements experiments usually are analyzed either as a univariate analysis of variance or using a multivariate analysis. Only the multivariate analysis is correct for all normal errors, but the univariate analysis of variance has greater power for certain covariance structures. Using an approximation to the distribution of the analysis of variance test statistic, the power of these competing tests is compared.
No takes yet. Share an insight, caveat, or question.
Mark Marcucci (1986) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: