Testing for main fixed effects: The symmetry assumption and monotone incomplete data

Abstract

We consider the balanced two-way mixed effects design with some empty cells. A test procedure for the hypothesis of no main fixed effects is developed under violation of the assumption of variance homogeneity and symmetry. The asymptotic null distribution of the test statistics is studied under the condition that the number of levels of the random effects tends to infinity as both the number of complete and incomplete observations tend to infinity. An illustrative example is given.