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. 1603.09000
14
105

Online Rules for Control of False Discovery Rate and False Discovery Exceedance

29 March 2016
Adel Javanmard
Andrea Montanari
ArXivPDFHTML
Abstract

Multiple hypothesis testing is a core problem in statistical inference and arises in almost every scientific field. Given a set of null hypotheses H(n)=(H1,…,Hn)\mathcal{H}(n) = (H_1,\dotsc, H_n)H(n)=(H1​,…,Hn​), Benjamini and Hochberg introduced the false discovery rate (FDR), which is the expected proportion of false positives among rejected null hypotheses, and proposed a testing procedure that controls FDR below a pre-assigned significance level. Nowadays FDR is the criterion of choice for large scale multiple hypothesis testing. In this paper we consider the problem of controlling FDR in an "online manner". Concretely, we consider an ordered --possibly infinite-- sequence of null hypotheses H=(H1,H2,H3,… )\mathcal{H} = (H_1,H_2,H_3,\dots )H=(H1​,H2​,H3​,…) where, at each step iii, the statistician must decide whether to reject hypothesis HiH_iHi​ having access only to the previous decisions. This model was introduced by Foster and Stine. We study a class of "generalized alpha-investing" procedures and prove that any rule in this class controls online FDR, provided ppp-values corresponding to true nulls are independent from the other ppp-values. (Earlier work only established mFDR control.) Next, we obtain conditions under which generalized alpha-investing controls FDR in the presence of general ppp-values dependencies. Finally, we develop a modified set of procedures that also allow to control the false discovery exceedance (the tail of the proportion of false discoveries). Numerical simulations and analytical results indicate that online procedures do not incur a large loss in statistical power with respect to offline approaches, such as Benjamini-Hochberg.

View on arXiv
Comments on this paper