Score Tests for Fixed Effects and Overdispersion Components in Nonlinear Models for Repeated Measures

A general nonlinear regression model for repeated measures data is considered. Neyman's [16] partial score tests are derived for the significance of regression parameters as well as overdispersion components of the model. Neyman's score test is asymptotically locally optimal, and the test statistic has asymptotically [chi]2 distribution under the null hypothesis, with m degrees of freedom, where m is the number of independent restrictions over the parameters, specified under the null hypothesis. The test for the regression parameters is illustrated by a numerical example.