Practical methods for computing power in testing the multivariate general linear hypothesis (Q1061479)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Practical methods for computing power in testing the multivariate general linear hypothesis |
scientific article |
Statements
Practical methods for computing power in testing the multivariate general linear hypothesis (English)
0 references
1984
0 references
Approximations (for the non-null mean case) to the following multivariate linear hypothesis tests are provided: Wilks, Hotelling, Pillai-Bartlett trace. These approximations use the non-central F distribution. Selection of a test statistic for experimental designs is made, and a table of notation equivalences for the tests and algorithms for power computation (direct and indirect) are given.
0 references
MANOVA
0 references
noncentral distributions
0 references
Wilks' lambda
0 references
Hotelling-Lawley trace
0 references
Pillai-Bartlett trace
0 references
F approximations
0 references
0 references
0 references
0 references
0 references
0 references
