High-Dimensional Multiple Testing of Dependent, Discrete, and Heterogeneous Data

• Activity Number: 332
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
• Sponsor: IMS
• Author(s): Joshua Habiger*+
• Companies: Oklahoma State University
• Keywords: multiple testing ; high dimensional data ; dependence ; heterogeneity ; discrete ; false discovery rate

Abstract

High dimensional (HD) data sets that call for hundreds or thousands of hypotheses to be tested simultaneously are increasingly prevalent and pose a variety of challenges. In particular, many multiple testing procedures assume data are continuous, independent and identically distributed under the null hypotheses when in reality data are often discrete, dependent and/or heterogeneous. Routes for exploiting or accounting for heterogeneity, dependence and the discreteness of the data in HD multiple testing are discussed.