Cited by 613Statistical Methods in Clinical TrialsStatistical Methods and InferenceProbability and Statistical Research

Exact and Approximate Stepdown Methods for Multiple Hypothesis Testing

Open access
Romano, Joseph P, Wolf, Michael·2005·Journal of the American Statistical Association

Abstract

Consider the problem of testing k hypotheses simultaneously. In this article we discuss finite- and large-sample theory of stepdown methods that provide control of the familywise error rate (FWE). To improve on the Bonferroni method or on Holm's stepdown method, Westfall and Young made effective use of resampling to construct stepdown methods that implicitly estimate the dependence structure of the test statistics. However, their methods depend on an assumption known as “subset pivotality.” Our goal here is to construct general stepdown methods that do not require such an assumption. To accomplish this, we take a close look at what makes stepdown procedures work; a key component is a monotonicity requirement of critical values. By imposing monotonicity on estimated critical values (which is not an assumption on the model but rather is an assumption on the method), we show how to construct stepdown tests that can be applied in a stagewise fashion so that at most k tests need to be computed. Moreover, at each stage, an intersection test that controls the usual probability of a type 1 error is calculated, which allows us to draw on an enormous resampling literature as a general means of test construction. In addition, it is possible to carry out this method using the same set of resamples (or subsamples) for each of the intersection tests.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1198/016214504000000539

Cites

23 of 23 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 3

  1. Hochberg, Y. and Tamhane, A. (1987). Multple Comparison Procedures. Wiley, New York.
  2. Politis, D. N., Romano, J. P., and Wolf, M. (1999). Subsampling. Springer, New York.
  3. Westfall, P. H. and Young, S. S. (1993). Resampling-Based Multiple Testing: Examples and Methods for P-Value Adjustment. John Wiley, New York.

Cited by

Sorted by citations

Authors
Romano, J. P., & Wolf, M.
Affiliations
Stanford University (US)
Venue
Journal of the American Statistical Association
Published
2005-03
Volume
100
Issue
469
Pages
94-108
ISSN
  • 0162-1459 (ISSN-L)
  • 1537-274X
OpenAlex
W3124231044
Cited by
609
References
23
Citations by year
2026: 44 · 2025: 63 · 2024: 51 · 2023: 52 · 2022: 60 · 2021: 47 · 2020: 38 · 2019: 33 · 2018: 38 · 2017: 29 · 2016: 25 · 2015: 15 · 2014: 22 · 2013: 11 · 2012: 14
FWCI
10.03
Type
journal article
Language
en
Open access
Locations
  • Journal of the American Statistical Association (publishedVersion)
  • SSRN Electronic Journal (acceptedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • Repositori digital de la UPF (Universitat Pompeu Fabra) (submittedVersion, cc-by-nc-nd)
  • RECERCAT (Consorci de Serveis Universitaris de Catalunya) (submittedVersion, other-oa)
Funders
  • National Science Foundation
  • Ministerio de Ciencia y Tecnología
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
  • Physical Sciences › Mathematics › Statistics and Probability › Probability and Statistical Research
Keywords
multiple comparisons, family-wise error rate, resampling, Bonferroni correction, intersection tests, asymptotic theory

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review