Anchored multiple testing: a transparent use of e-closure to improve FDR procedures

2026-10-08

AI Summary

This study addresses the limitations of the e-closure method, including its strong self-referentiality, lack of actionable insights for improvement, and procedural opacity, by proposing an "anchoring" technique. This approach exploits the slackness in existing false discovery rate (FDR) proofs to amplify local e-values, integrating sorting and quadratic-time algorithmic optimizations to construct a unified framework grounded in e-closure theory. The resulting framework enables transparent enhancements of baseline multiple testing procedures. Experimental results demonstrate that, while maintaining equivalent FDR control, the proposed technique significantly outperforms mainstream procedures such as Benjamini-Hochberg (BH) and Benjamini-Yekutieli (BY). Furthermore, it remains compatible with diverse dependence structures, establishing a novel paradigm for FDR control that successfully combines theoretical rigor with practical utility.

Abstract

The recent e-closure method can recover every procedure that controls FDR (and other expectation losses). But the recovered e-collection is ``self-referential'' and gives no insight on how to improve the procedure (if improvable), and some recent improvements have been somewhat opaque. We introduce an elementary new technique called anchoring that exploits looseness in existing FDR proofs to enlarge a baseline multiple-testing procedure's self-referential local e-value. The resulting e-closure thus transparently retains every baseline discovery (and usually adding more) and controlling the false discovery rate under the same conditions as the baseline. To show that this principle is broadly applicable, we use it to improve a large suite of multiple testing procedures: (i) Anchored-BH dominates the Benjamini-Hochberg (BH) procedure under PRDS while being incomparable to Goeman's recent closed-BH, (ii) Anchored-BY dominates the Benjamini-Yekutieli (BY) procedure under arbitrary dependence while being incomparable to closed-BY, (iii) For two-sided Gaussian p-values (under appropriate covariance conditions), Anchored-2BH dominates running BH twice at half the level on two one-sided p-values, (iv) Anchored-dBH dominates dependence-adjusted BH, (v) Anchored e-BH dominates e-BH and is incomparable to closed e-BH, (vi) Anchored SeqStep+ improves the original (including selective and adpative variants) while preserving ordered rejection structures. All of these are accomplished in sorting or quadratic time. The appendix shows how to dominate Shifted-BH (for two-sided arbitrarily correlated Gaussians) and NDBH (under negative dependent p-values).

Innovation

• anchored multiple testing
• e-closure
• false discovery rate
• local e-value
• multiple testing procedures