Home > Research > Publications & Outputs > QuickMMCTest

Electronic data

  • quick

    Rights statement: © Springer Science+Business Media New York 2016. The final publication is available at Springer via http://dx.doi.org/10.1007/s11222-016-9656-z

    Accepted author manuscript, 141 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

QuickMMCTest: quick multiple Monte Carlo testing

Research output: Contribution to journalJournal articlepeer-review

Published
<mark>Journal publication date</mark>4/05/2017
<mark>Journal</mark>Statistics and Computing
Issue number3
Volume27
Number of pages10
Pages (from-to)823-832
Publication StatusPublished
Early online date1/05/16
<mark>Original language</mark>English

Abstract

Multiple hypothesis testing is widely used to evaluate scientific studies involving statistical tests. However, for many of these tests, p values are not available and are thus often approximated using Monte Carlo tests such as permutation tests or bootstrap tests. This article presents a simple algorithm based on Thompson Sampling to test multiple hypotheses. It works with arbitrary multiple testing procedures, in particular with step-up and step-down procedures. Its main feature is to sequentially allocate Monte Carlo effort, generating more Monte Carlo samples for tests whose decisions are so far less certain. A simulation study demonstrates that for a low computational effort, the new approach yields a higher power and a higher degree of reproducibility of its results than previously suggested methods.

Bibliographic note

© Springer Science+Business Media New York 2016. The final publication is available at Springer via http://dx.doi.org/10.1007/s11222-016-9656-z