Additional power computations for designing comparative Poisson trials.

Published power computations for designing comparative Poisson trials are extended to the case of unequal populations sizes. The goal is to determine the required duration of a study for testing the one-sided alternative that the incidence rate of a rare disease in one population exceeds that in another population, based on an exact test conditional on the total number of events observed. Tables are provided for two designs: observing until a predetermined number of events have been observed, or observing for a predetermined length of time. The results may also be used to determine sample sizes for comparative binomial trials with very small binomial parameters when the numbers of patients in the two groups are not necessarily equal.