Title: Executive Director, Biostatistics and Research Decision Sciences
Institution: Merck Research Laboratories
Street: 785 Jolly Road
City: Blue Bell, PA
Authors: Devan Mehrotra Joseph Heyse
Title: Use of the False Discovery Rate for Evaluating of Clinical Safety Data
Abstract: Analyses of clinical adverse event (AE) data are routinely summarized using between-group p-values for every AE within each of several body systems. If p-values are reported and/or interpreted without multiplicity considerations, there is a potential for too many false positive findings. This can needlessly muddy the safety profile of an otherwise safe drug or vaccine. Accordingly, we offer an innovative proposal for tackling multiplicity, one that provides a reasonable balance between no adjustment and over adjustment, and is easy to automate. Our proposal involves a two-step use of adjusted p-values based on the false discovery rate (FDR) methodology of Benjamini and Hochberg (1995). Real data from three moderate to large vaccine clinical trials are used to illustrate our proposed ?Double FDR? approach and to reinforce the potential impact of failing to account for multiplicity in the safety setting. This work was in collaboration with the late Professor ! John W. Tukey who coined the term ?Double FDR?.
References: Benjamini and Hochberg (1995). Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society, Series B, 57, 289-300.