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. 2408.11307
31
4

Improved thresholds for e-values

21 August 2024
Christopher Blier-Wong
Ruodu Wang
ArXivPDFHTML
Abstract

The rejection threshold used for e-values and e-processes is by default set to 1/α1/\alpha1/α for a guaranteed type-I error control at α\alphaα, based on Markov's and Ville's inequalities. This threshold can be wasteful in practical applications. We discuss how this threshold can be improved under additional distributional assumptions on the e-values; some of these assumptions are naturally plausible and empirically observable, without knowing explicitly the form or model of the e-values. For small values of α\alphaα, the threshold can roughly be improved (divided) by a factor of 222 for decreasing or unimodal densities, and by a factor of eee for decreasing or unimodal-symmetric densities of the log-transformed e-value. Moreover, we propose to use the supremum of comonotonic e-values, which is shown to preserve the type-I error guarantee. We also propose some preliminary methods to boost e-values in the e-BH procedure under some distributional assumptions while controlling the false discovery rate. Through a series of simulation studies, we demonstrate the effectiveness of our proposed methods in various testing scenarios, showing enhanced power.

View on arXiv
Comments on this paper