Inference on the rate ratio of recurrent events for the matched pairs design

As statistical methods for testing the null hypothesis of no difference between two groups for the matched pairs design, the paired-t test, Wilcoxon signed rank sum test and McNemar test are well known. However, there is no simple test for the comparison of incidence rate of recurrent events. This paper proposes a simple statistical method and a sample size formula for the comparison of counts of recurrent events over a specified period of observation under the matched pairs design, where the subject-specific incidence of recurrent events is assumed to follow a time-homogeneous Poisson process. As a special case, the proposed method is found to be virtually equivalent in form to Mantel-Haenszel method for a common rate ratio among the set of stratified tables based on person-time data. The proposed methods are illustrated with the within-arm comparison of data from a clinical trial of 59 epileptics with baseline count data.