A comparison is made between analysis of covariance solutions obtained under the univariate and multivariate models in the case where an experimental design contains between- and within-subject factors, one dependent variable, and one observation per subject on the covariate. Modifications of analysis of variance procedures are described which yield exact ANCOVA solutions from ANOVAs performed on residual scores.
No takes yet. Share an insight, caveat, or question.
Ceurvorst et al. (1978) studied this question.