A mixture of the MANOVA and GMANOVA models is presented. The expected value of the response matrix in this model is the sum of two matrix components. The first component represents the GMANOVA portion and the second component represents the MANOVA portion. Maximum likelihood estimators are derived for the parameters in this model, and goodness-of-fit tests are constructed for fuller models via the likelihood ratio criterion. Finally, likelihood ratio tests for general linear hypotheses are developed and a numerical example is presented.
All Science Journal Classification (ASJC) codes
- Statistics and Probability