Meta-analysis of Clinical Trials with Sparse Binary Outcomes using Zero-inflated Binomial Models
Cheng Dong, University of Missouri  Ram Tiwari, FDA/CDRH  *Yueqin Zhao, U.S. Food and Drug Administration 

Keywords: safety trial, rare events, EM algorithm

In meta-analysis of clinical trials, standard statistical methods run into problems when the proportions of safety events are small. Motivated by the dataset used in a published analysis of cardiovascular safety in Rosiglitazone trials, this talk used zero-inflated Binomial (ZIB) model to handle the zero event trials. The maximum likelihood estimates of the model parameters were obtained using the expectation and maximization algorithm. Via simulation studies, it is shown that the proposed methods provide estimates of odds ratios with less bias and variation, compared with Mantel-Hanszel methods with continuity correction and Peto methods. The proposed methods were applied to the Rosiglitazone trials.