ERIC Number: ED379296
Record Type: Non-Journal
Publication Date: 1994-Oct
Reference Count: N/A
Choosing a MANOVA Test Statistic When Covariances Are Unequal.
Beasley, T. Mark; Sheehan, Janet K.
C. L. Olson (1976, 1979) suggests the Pillai-Bartlett trace (V) as an omnibus multivariate analysis of variance (MANOVA) test statistic for its superior robustness to heterogeneous variances. J. Stevens (1979, 1980) contends that the robustness of V, Wilk's lambda (W) and the Hotelling-Lawley trace (T) are similar, and that their power functions are highly sensitive to slight covariance inequalities. Yet under conditions of diffuse noncentrality structures, V is a clear choice. A Monte Carlo simulation of V, W, and T as omnibus tests under conditions of covariance heterogeneity and variance homogeneity investigates the robustness of each test. Conditions of concentrated covariance and noncentrality structure were imposed to compare power. Results indicate that the assumption of homogeneous variance-covariance matrices in the form of covariance inequalities does not affect the robustness of V, W, or T, while T is slightly more powerful under such conditions. Five tables are included. (Contains 14 references.) (Author/SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A