Testing Goodness of Fit for the Poisson Assumption When Observations Are Not Identically Distributed

Abstract

Tests for detecting negative binomial departures from a Poisson model are studied for the one-way-layout and regression-through-the-origin cases. Approximations to the null and alternative distributions of these test statistics are presented. Locally optimal tests and tests suggested in the literature are compared in terms of asymptotic relative efficiency. Small sample comparisons are included.