ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2106.13501
11
14

Semi-supervised multiple testing

25 June 2021
D. Mary
Étienne Roquain
ArXivPDFHTML
Abstract

An important limitation of standard multiple testing procedures is that the null distribution should be known. Here, we consider a null distribution-free approach for multiple testing in the following semi-supervised setting: the user does not know the null distribution, but has at hand a sample drawn from this null distribution. In practical situations, this null training sample (NTS) can come from previous experiments, from a part of the data under test, from specific simulations, or from a sampling process. In this work, we present theoretical results that handle such a framework, with a focus on the false discovery rate (FDR) control and the Benjamini-Hochberg (BH) procedure. First, we provide upper and lower bounds for the FDR of the BH procedure based on empirical ppp-values. These bounds match when α(n+1)/m\alpha (n+1)/mα(n+1)/m is an integer, where nnn is the NTS sample size and mmm is the number of tests. Second, we give a power analysis for that procedure suggesting that the price to pay for ignoring the null distribution is low when nnn is sufficiently large in front of mmm; namely n≳m/(max⁡(1,k))n\gtrsim m/(\max(1,k))n≳m/(max(1,k)), where kkk denotes the number of ``detectable'' alternatives. Third, to complete the picture, we also present a negative result that evidences an intrinsic transition phase to the general semi-supervised multiple testing problem {and shows that the empirical BH method is optimal in the sense that its performance boundary follows this transition phase}. Our theoretical properties are supported by numerical experiments, which also show that the delineated boundary is of correct order without further tuning any constant. Finally, we demonstrate that our work provides a theoretical ground for standard practice in astronomical data analysis, and in particular for the procedure proposed in \cite{Origin2020} for galaxy detection.

View on arXiv
Comments on this paper