Skip to content

Research at St Andrews

A non-parametric maximum test for the Behrens–Fisher problem

Research output: Contribution to journalArticle

Standard

A non-parametric maximum test for the Behrens–Fisher problem. / Welz, Anke; Ruxton, Graeme D.; Neuhäuser, Markus.

In: Journal of Statistical Computation and Simulation, Vol. 88, No. 7, 03.2018, p. 1336-1347.

Research output: Contribution to journalArticle

Harvard

Welz, A, Ruxton, GD & Neuhäuser, M 2018, 'A non-parametric maximum test for the Behrens–Fisher problem' Journal of Statistical Computation and Simulation, vol. 88, no. 7, pp. 1336-1347. https://doi.org/10.1080/00949655.2018.1431236

APA

Welz, A., Ruxton, G. D., & Neuhäuser, M. (2018). A non-parametric maximum test for the Behrens–Fisher problem. Journal of Statistical Computation and Simulation, 88(7), 1336-1347. https://doi.org/10.1080/00949655.2018.1431236

Vancouver

Welz A, Ruxton GD, Neuhäuser M. A non-parametric maximum test for the Behrens–Fisher problem. Journal of Statistical Computation and Simulation. 2018 Mar;88(7):1336-1347. https://doi.org/10.1080/00949655.2018.1431236

Author

Welz, Anke ; Ruxton, Graeme D. ; Neuhäuser, Markus. / A non-parametric maximum test for the Behrens–Fisher problem. In: Journal of Statistical Computation and Simulation. 2018 ; Vol. 88, No. 7. pp. 1336-1347.

Bibtex - Download

@article{813ee6626fd44be1a93968a4e7ceb514,
title = "A non-parametric maximum test for the Behrens–Fisher problem",
abstract = "Non-normality and heteroscedasticity are common in applications. For the comparison of two samples in the non-parametric Behrens-Fisher problem, different tests have been proposed, but no single test can be recommended for all situations. Here, we propose combining two tests, the Welch t test based on ranks and the Brunner-Munzel test, within a maximum test. Simulation studies indicate that this maximum test, performed as a permutation test, controls the type I error rate and stabilizes the power. That is, it has good power characteristics for a variety of distributions, and also for unbalanced sample sizes. Compared to the single tests, the maximum test shows acceptable type I error control.",
keywords = "Behrens-Fisher problem, Brunner-Munzel test, Maximum test, Welch t test",
author = "Anke Welz and Ruxton, {Graeme D.} and Markus Neuh{\"a}user",
year = "2018",
month = "3",
doi = "10.1080/00949655.2018.1431236",
language = "English",
volume = "88",
pages = "1336--1347",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis",
number = "7",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A non-parametric maximum test for the Behrens–Fisher problem

AU - Welz, Anke

AU - Ruxton, Graeme D.

AU - Neuhäuser, Markus

PY - 2018/3

Y1 - 2018/3

N2 - Non-normality and heteroscedasticity are common in applications. For the comparison of two samples in the non-parametric Behrens-Fisher problem, different tests have been proposed, but no single test can be recommended for all situations. Here, we propose combining two tests, the Welch t test based on ranks and the Brunner-Munzel test, within a maximum test. Simulation studies indicate that this maximum test, performed as a permutation test, controls the type I error rate and stabilizes the power. That is, it has good power characteristics for a variety of distributions, and also for unbalanced sample sizes. Compared to the single tests, the maximum test shows acceptable type I error control.

AB - Non-normality and heteroscedasticity are common in applications. For the comparison of two samples in the non-parametric Behrens-Fisher problem, different tests have been proposed, but no single test can be recommended for all situations. Here, we propose combining two tests, the Welch t test based on ranks and the Brunner-Munzel test, within a maximum test. Simulation studies indicate that this maximum test, performed as a permutation test, controls the type I error rate and stabilizes the power. That is, it has good power characteristics for a variety of distributions, and also for unbalanced sample sizes. Compared to the single tests, the maximum test shows acceptable type I error control.

KW - Behrens-Fisher problem

KW - Brunner-Munzel test

KW - Maximum test

KW - Welch t test

U2 - 10.1080/00949655.2018.1431236

DO - 10.1080/00949655.2018.1431236

M3 - Article

VL - 88

SP - 1336

EP - 1347

JO - Journal of Statistical Computation and Simulation

T2 - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 7

ER -

Related by author

  1. Deconstructing collective building in social insects: implications for ecological adaptation and evolution

    Invernizzi, E. & Ruxton, G. D., 8 Aug 2019, In : Insectes Sociaux. First Online, 12 p.

    Research output: Contribution to journalReview article

  2. The Hermans–Rasson test as a powerful alternative to the Rayleigh test for circular statistics in biology

    Landler, L., Ruxton, G. D. & Malkemper, E. P., 7 Aug 2019, In : BMC Ecology. 19, 8 p., 30.

    Research output: Contribution to journalArticle

  3. A theory for investment across defences triggered at different stages of a predator-prey encounter

    Wang, L., Ruxton, G. D., Cornell, S. J., Speed, M. P. & Broom, M., 21 Jul 2019, In : Journal of Theoretical Biology. 473, p. 9-19 11 p.

    Research output: Contribution to journalArticle

  4. Secondary dispersal mechanisms of winged seeds: a review

    der Weduwen, D. & Ruxton, G. D., 19 Jun 2019, In : Biological Reviews. Early View, 9 p.

    Research output: Contribution to journalReview article

  5. Circular statistics meets practical limitations: a simulation-based Rao’s spacing test for non-continuous data

    Landler, L., Ruxton, G. D. & Malkemper, E. P., 10 May 2019, In : Movement Ecology. 7, 5 p., 15.

    Research output: Contribution to journalArticle

Related by journal

  1. Bayesian P-splines and advanced computing in R for a changepoint analysis on spatio-temporal point processes

    Altieri, L., Cocchi, D., Greco, F., Illian, J. B. & Scott, E. M., 2016, In : Journal of Statistical Computation and Simulation. 86, 13, p. 2531-2545 15 p.

    Research output: Contribution to journalArticle

  2. SALSA – A Spatially Adaptive Local Smoothing Algorithm

    Walker, C., MacKenzie, M. L., Donovan, C. R. & O'Sullivan, M., Feb 2011, In : Journal of Statistical Computation and Simulation. 81, 2, p. 179-191

    Research output: Contribution to journalArticle

ID: 252572639