POWER CALCULATIONS FOR LIKELIHOOD RATIO TESTS IN GENERALIZED LINEAR-MODELS

Recently Self and Mauritsen (1988, Biometrics 44, 79-86) described an approach for sample size/power calculations within the framework of generalized linear models that is based on a noncentral chi-square approximation to the distribution of score statistics. In this work, we present another approach to this same problem that is based on a noncentral chi-square approximation to the distribution of the likelihood ratio statistic. This approach is easier to implement than the previous one and simulation studies indicate that it is accurate over a much wider range of parameter values and data configurations than the earlier method. The new method is also applied to the problem of power calculations for 1:K matched case-control studies which is related to, but formally outside of, the generalized linear model framework.