|
Abstract:
|
This paper develops procedures for testing the homogeneity of the means of several groups of count data with overdispersion. The score type tests based on the models that are specified by only the first two moments of the counts are obtained using quasi-likelihood (QL), extended quasi-likelihood (EQL), and double extended quasi-likelihood (DEQL). Simulations are then used to study the comparative behavior of these statistics compared to the statistic based on the negative binomial model, in terms of size, power and robustness for departures from the data. These simulations demonstrate that the statistic based on the DEQL holds the nominal level well, and it shows some edge in power over the other statistics, and, in particular, it performs much better than the commonly used statistic based on the QL. Finally, applications to toxicological and biological data are given.
|
