Adjusting the Benjamini-Hochberg method for controlling the false\n discovery rate in knockoff assisted variable selection

2021/02/17 by Sanat K. Sarkar, Sarkar, Sanat K., Cheng Yong Tang +1 · 1 citation
Mathematics · #FOS: Computer and information sciences #Methodology (stat.ME) #Statistical Methods and Bayesian Inference #Statistical Methods and Inference #Statistical Methods in Clinical Trials

paper · pdf · doi:10.48550/arxiv.2102.09080

openalex publication_date 2021/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The knockoff-based multiple testing setup of Barber & Candes (2015) for\nvariable selection in multiple regression where sample size is as large as the\nnumber of explanatory variables is considered. The method of Benjamini &\nHochberg (1995) based on ordinary least squares estimates of the regression\ncoefficients is adjusted to the setup, transforming it to a valid p-value based\nfalse discovery rate controlling method not relying on any specific correlation\nstructure of the explanatory variables. Simulations and real data applications\nshow that our proposed method that is agnostic to \π0, the proportion of\nunimportant explanatory variables, and a data-adaptive version of it that uses\nan estimate of \π0 are powerful competitors of the false discovery rate\ncontrolling method in Barber & Candes (2015).\n

Cited by

• Controlling the false discovery rate in high-dimensional linear models using model-X knockoffs and p-values

Related

• Controlling the FDR in variable selection via multiple knockoffs
• Controlling the false discovery rate in high-dimensional linear models using model-X knockoffs and p-values
• One-at-a-time knockoffs: controlled false discovery rate with higher power
• A Complete Review of Controlling the FDR in a Multiple Comparison Problem Framework -- The Benjamini-Hochberg Algorithm
• Local False Discovery Rate Estimation with Competition-Based Procedures for Variable Selection