Power Analysis for Sparse Signal Recovery in Genome-Wide Association

• Activity Number: 4
• Type: Invited
• Date/Time: Sunday, July 31, 2011 : 2:00 PM to 3:50 PM
• Sponsor: ENAR
• Author(s): Hongzhe Li*+ and Jichun Xie and Tony Cai
• Companies: University of Pennsylvania and University of Pennsylvania and University of Pennsylvania
• Keywords: FDR ; high dimensional data ; oracle property ; multiple testing

Abstract

Genome-wide association studies (GWAS) have successfully identified hundreds of novel genetic variants associated with many complex human diseases. However, there is a lack of rigorous work on evaluating the statistical power for identifying the disease-associated SNPs in GWAS. In this paper, we consider the problem of sparse signal identification in GWAS and present two analytical frameworks for detailed analysis of the statistical power for detecting and identifying the disease-associated SNPs. We present an explicit sample size formula for achieving a given false non-discovery rate while controlling the false discovery rate based on an optimal false discovery procedure. The problem of sparse SNP recovery is also considered and boundary condition is established in term of sparsity and signal strength for almost full recovery of both disease-associated SNPs and nondisease-associated SNPs. A data-adaptive procedure is proposed to achieve this bound. These results provide important tools for sample size calculation and power analysis for GWAS. The analytical results are illustrated with a genome-wide association study of neuroblastoma.