Near-optimal multiple testing in Bayesian linear models with finite-sample FDR control

TL;DR

This paper introduces a new multiple testing procedure, PoEdCe, for Bayesian linear models that controls FDR in finite samples and aims to maximize discoveries, supported by theoretical and numerical evidence.

Contribution

It develops a near-optimal, finite-sample FDR controlling method for Bayesian linear models that is robust to model misspecification and combines several advanced statistical techniques.

Findings

PoEdCe controls FDR in finite samples.

Supports near-optimal power conjecture for Bayesian models.

Establishes Bayesian linear models as a benchmark for testing procedures.

Abstract

In high dimensional variable selection problems, statisticians often seek to design multiple testing procedures that control the False Discovery Rate (FDR), while concurrently identifying a greater number of relevant variables. Model-X methods, such as Knockoffs and conditional randomization tests, achieve the primary goal of finite-sample FDR control, assuming a known distribution of covariates. However, whether these methods can also achieve the secondary goal of maximizing discoveries remains uncertain. In fact, designing procedures to discover more relevant variables with finite-sample FDR control is a largely open question, even within the arguably simplest linear models. In this paper, we develop near-optimal multiple testing procedures for high dimensional Bayesian linear models with isotropic covariates. We introduce Model-X procedures that provably control the frequentist FDR from finite samples, even when the model is misspecified, and conjecturally achieve near-optimal power when the data follow the Bayesian linear model. Our proposed procedure, PoEdCe, incorporates three key ingredients: Posterior Expectation, distilled Conditional randomization test (dCRT), and the Benjamini-Hochberg procedure with e-values (eBH). The optimality conjecture of PoEdCe is based on a heuristic calculation of its asymptotic true positive proportion (TPP) and false discovery proportion (FDP), which is supported by methods from statistical physics as well as extensive numerical simulations. Our result establishes the Bayesian linear model as a benchmark for comparing the power of various multiple testing procedures.