New testing procedures with k-FWER control for discrete data

Li Wang

Statistics & Probability Letters, 2022, vol. 180, issue C

Abstract: Discrete p-values are often encountered in clinical studies and genomic studies, where Fisher’s exact test or binomial test is used. Since the distributions of the p-values for discrete data are discrete, and can be heterogeneous and stochastically larger than Uniform distribution U[0,1] under the null hypotheses, the multiple testing procedure constructed for continuous p-values will be conservative when applied to discrete data. This paper will propose new procedures with k-FWER control, the probability of making no less than k false discoveries, by using the cumulative distribution function of the p-values and improving generalized Bonferroni and generalized Holm procedure for arbitrarily dependent p-values. Extensive simulations and real data analysis will demonstrate the power improvement of the newly proposed procedures.

Keywords: Discrete data; k-FWER; Multiple testing (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S016771522100198X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:stapro:v:180:y:2022:i:c:s016771522100198x

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

DOI: 10.1016/j.spl.2021.109236

Access Statistics for this article

Statistics & Probability Letters is currently edited by Somnath Datta and Hira L. Koul

More articles in Statistics & Probability Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().