ABSTRACT
This chapter explains the idea of Tse to derive likelihood ratio tests for homogeneity of zero-inflated Poisson (ZIP) populations under the null hypotheses that there is no difference in the group of zeros, there is no difference in the group of nonzeros, and there is no difference in both groups of zeros and nonzeros. Under appropriate alternative hypotheses, approximate formulas for sample size calculation are obtained for achieving a desired power for detecting a clinically meaningful difference at a prespecified level of significance. The chapter describes the procedure for sample size calculation and an example concerning the assessment of the gastrointestinal (GI) safety in terms of the number of erosion counts of a newly developed compound for the treatment of osteoarthritis (OA) and rheumatoid arthritis (RA). It considers the test for the treatment effect under multivariate (bivariate) ZIP model.
