A monte carlo study of the power of alternative tests under the generalized manova model |
| |
Authors: | Martijn P.F. Berger |
| |
Affiliation: | University of Til burg , Postbus 90153, LE Tilburg, 5000, The Netherlands |
| |
Abstract: | Monte Carlo simulations are performed for a broad range of conditions. These simulations indicate that the powers of alternative tests under the generalized MANOVA model for small samples differ significantly, if a large reduction of the number of polynomial parameters is applied. The results show that, if the response covariance matrix ∑ is known, the best alternative is to use ∑. If, however, ∑ is unknown, substitution of an identity matrix for ∑ is recommended. This alternative usually results in a test with more power than the test with the usual estimate of ∑ employing covariates or the test with an estimate of E obtained from another sample. |
| |
Keywords: | generalized growth curve model MANOVA Monte carlo multivariate test power function |
|
|