A simulation study to resolve conflicting evidence on the error rates from MANOVA group tests

Popular software packages report four generalizations of the ANOVA F test when conducting a multivariate analysis of variance (MANOVA). The reported operating characteristics of these fours tests vary widely depending on which research article the reader chooses. Certain studies report extremely high type I error rates for a particular test even under ideal assumptions of multivariate normality and homoskedasticity; others report rates near the nominal level despite violations of the model assumptions. This simulation study seeks to clarify this apparent contradiction by providing a systematic evaluation of the type I error rates of the four statistics used to test for a group effect in MANOVA.