An Empirical Study of the Type I Error Rates of Five Multivariate Tests for the Single-Factor Repeated Measures Model.

A Monte Carlo study was used to examine the Type I error rates of five multivariate tests for the single-factor repeated measures model. The performance of Hotelling's T-squared and four nonparametric tests, including a chi-square and an "F" test version of a rank-transform procedure, was investigated for different distributions, sample sizes, and numbers of repeated measures. The results indicated that both Hotelling's T-squared and the F test version of the rank-transform test performed well, producing Type I error rates that were close to the nominal value. The chi-square version of the rank-transform test, on the other hand, performed poorly for virtually all conditions studied. The performance of the other nonparametric tests depended heavily on sample size. Based on these results, Hotelling's T-squared is recommended for the single-factor repeated measures model. Appendix A discusses computing the tests. (Contains 1 table and 48 references.) (Author/SLD)