Results on a Robust Class of Multiple Testing Procedure

• Activity Number: 418
• Type: Topic Contributed
• Date/Time: Tuesday, August 11, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Scientific and Public Affairs Advisory Committee
• Author(s): Nasrine Bendjilali* and Boualem Bendjilali and Wei-Min Huang
• Companies: Rowan University and RVCC and Lehigh University
• Keywords: multiple testing procedures ; p-value

Abstract

Recent advances in biotechnology routinely produce hundreds of thousands of hypotheses to be tested simultaneously. In practice, the high-dimensional data generated has unknown dependent structure and not taking the dependence structure into account will lead to conservative results. In this study, we introduce a robust class of multiple testing procedure that incorporates the underlying dependence structures of the p-values. The new procedure uses a transformation of the p-values with unique properties. In this paper, we examine the various properties of the proposed procedure and its performance. The procedure's theoretical and simulation results of its performance under various dependence structures and power will be presented.