New FDR bounds for discrete and heterogeneous tests - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Electronic Journal of Statistics Année : 2018

New FDR bounds for discrete and heterogeneous tests

Résumé

To find interesting items in genome-wide association studies or next generation sequencing data, a crucial point is to design power- ful false discovery rate (FDR) controlling procedures that suitably com- bine discrete tests (typically binomial or Fisher tests). In particular, recent research has been striving for appropriate modifications of the classical Benjamini-Hochberg (BH) step-up procedure that accommodate discrete- ness and heterogeneity of the data. However, despite an important number of attempts, these procedures did not come with theoretical guarantees. In this paper, we provide new FDR bounds that allow us to fill this gap. More specifically, these bounds make it possible to construct BH-type procedures that incorporate the discrete and heterogeneous structure of the data and provably control the FDR for any fixed number of null hypotheses (under independence). Markedly, our FDR controlling methodology also allows to incorporate the quantity of signal in the data (corresponding therefore to a so-called π0-adaptive procedure) and to recover some prominent results of the literature. The power advantage of the new methods is demonstrated in a numerical experiment and for some appropriate real data sets.
Fichier principal
Vignette du fichier
DDR2018_published.pdf (503.8 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01541185 , version 1 (18-06-2017)
hal-01541185 , version 2 (14-09-2017)
hal-01541185 , version 3 (27-12-2022)

Identifiants

Citer

Sebastian Döhler, Guillermo Durand, Etienne Roquain. New FDR bounds for discrete and heterogeneous tests: New FDR bounds for discrete and heterogeneous tests. Electronic Journal of Statistics , 2018, ⟨10.1214/18-EJS1441⟩. ⟨hal-01541185v3⟩
687 Consultations
310 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More