|
Abstract:
|
Meta analysis (MA) is commonly used in the post-marketing safety studies of FDA regulated medical products, including drugs, medical device, and etc. Avandia Studies is a powerful example to show how important MA is in real life for quantifying the safety concerns with policy impacts. However, the fact that the re-analysis of same Avandia data could reach different conclusions showed the statistical challenges associated with standard fixed and random effect MA methods for combining trails with extremely rare events. Specifically, the inclusion and exclusion of zero trials, low power in homogeneity test associated with standard approaches and limited interpretability of popular MA estimands using OR due to non-collapsibility. And, various types of add-hoc continuation corrections were widely used to improve the performance of standard MA estimators. In this paper, we proposed a marginal meta analysis approach with natural weights which provided a consistent estimates for marginal causal effects combining randomized clinical trials without continuation corrections, and address some of those challenges. Joint work with Elande Baro, Yun-Yu Cheng, and Guoxing Soon from FDA.
|
