Activity Number:
|
484
- Methods for High-Dimensional Data in Genetics and Genomics
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Biometrics Section
|
Abstract #311052
|
|
Title:
|
Covariate Adaptive Family-Wise Error Rate Control for Genome-Wide Association Studies
|
Author(s):
|
Huijuan Zhou* and Xianyang Zhang and Jun Chen
|
Companies:
|
Texas A&M University and Texas A&M University and Mayo Clinic
|
Keywords:
|
EM algorithm;
External covariates;
Family-wise error rate;
Multiple testing
|
Abstract:
|
Motivated by various applications in genomics studies where there are rich covariates that are informative of either the statistical power or the prior null probability, we propose a covariate adaptive family-wise error rate control procedure. We develop an efficient algorithm to implement the proposed method. We prove its asymptotic validity and obtain the convergence rate through a novel perturbation type argument. The numerical study shows that our procedure is more powerful than competing methods and maintains robustness across different settings. Finally, we apply the method to genome-wide association studies and demonstrate that our approach is capable of dealing with the big dataset and more competent to discover signals compared with existing methods.
|
Authors who are presenting talks have a * after their name.