False Discovery Rate Estimation for Large-Scale Homogeneous Discrete P-Values

• Activity Number: 456
• Type: Contributed
• Date/Time: Wednesday, August 6, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Kun Liang*+
• Keywords: Discrete p-values ; Dynamic adaptive methods ; False discovery rate ; Multiple testing

Abstract

Large-scale homogeneous discrete p-values are encountered frequently in high-throughput genomics studies, and the related multiple testing problems become challenging because most existing methods for the false discovery rate (FDR) control and estimation assume continuous $p$-values. In this paper, we advocate an FDR estimation approach that provides a direct and practical solution in the discrete p-value setting. In the finite sample setting, we propose a novel class of conservative FDR estimators. Furthermore, we show that a broad class of FDR estimators is simultaneously conservative over all support points under some weak dependence condition in the asymptotic setting.