A Levene-type test of homogeneity of variances against ordered alternatives

Philip Pallmann; Ludwig A. Hothorn; Gemechis D. Djira

doi:10.1007/s00180-014-0508-z

A Levene-type test of homogeneity of variances against ordered alternatives

Philip Pallmann^*, Ludwig A. Hothorn, Gemechis D. Djira

^*Corresponding author for this work

Department of Biostatistics

South Dakota State University

Research output: Contribution to journal › Article › Research › peer review

Abstract

Investigations focusing on differences in scale parameters across multiple samples appear in various scientific fields, e.g., when assessing measurement precision. In such cases a natural order of groups often suggests itself, which can be exploited by tests involving ordered alternatives. We propose multiple contrast tests with order-restriction based on robust Levene residuals as a powerful approach to detect scale differences between several groups. The proposed method is applied to a real data set and also extensive simulation is conducted to assess power and robustness against non-normality.

Original language	English
Pages (from-to)	1593-1608
Number of pages	16
Journal	Computational statistics
Volume	29
Issue number	6
DOIs	https://doi.org/10.1007/s00180-014-0508-z
Publication status	Published - 6 Jun 2014

Keywords

Multiple contrasts
Heterogeneous variances
Levene residuals
Order-restricted inference
Trend test

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty
Computational Mathematics

Access to Document

10.1007/s00180-014-0508-z

Cite this

@article{62ee776b269148f9af612066d68e9c57,

title = "A Levene-type test of homogeneity of variances against ordered alternatives",

abstract = "Investigations focusing on differences in scale parameters across multiple samples appear in various scientific fields, e.g., when assessing measurement precision. In such cases a natural order of groups often suggests itself, which can be exploited by tests involving ordered alternatives. We propose multiple contrast tests with order-restriction based on robust Levene residuals as a powerful approach to detect scale differences between several groups. The proposed method is applied to a real data set and also extensive simulation is conducted to assess power and robustness against non-normality.",

keywords = "Multiple contrasts, Heterogeneous variances, Levene residuals, Order-restricted inference, Trend test",

author = "Philip Pallmann and Hothorn, {Ludwig A.} and Djira, {Gemechis D.}",

note = "Funding Information: The work of the second author (LAH) was partly supported by the German Science Foundation grant DFG-HO1687. The authors wish to thank the editor and two anonymous referees for hints and suggestions that helped improve the manuscript. ",

year = "2014",

month = jun,

day = "6",

doi = "10.1007/s00180-014-0508-z",

language = "English",

volume = "29",

pages = "1593--1608",

journal = "Computational statistics",

issn = "0943-4062",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "6",

}

TY - JOUR

T1 - A Levene-type test of homogeneity of variances against ordered alternatives

AU - Pallmann, Philip

AU - Hothorn, Ludwig A.

AU - Djira, Gemechis D.

N1 - Funding Information: The work of the second author (LAH) was partly supported by the German Science Foundation grant DFG-HO1687. The authors wish to thank the editor and two anonymous referees for hints and suggestions that helped improve the manuscript.

PY - 2014/6/6

Y1 - 2014/6/6

N2 - Investigations focusing on differences in scale parameters across multiple samples appear in various scientific fields, e.g., when assessing measurement precision. In such cases a natural order of groups often suggests itself, which can be exploited by tests involving ordered alternatives. We propose multiple contrast tests with order-restriction based on robust Levene residuals as a powerful approach to detect scale differences between several groups. The proposed method is applied to a real data set and also extensive simulation is conducted to assess power and robustness against non-normality.

AB - Investigations focusing on differences in scale parameters across multiple samples appear in various scientific fields, e.g., when assessing measurement precision. In such cases a natural order of groups often suggests itself, which can be exploited by tests involving ordered alternatives. We propose multiple contrast tests with order-restriction based on robust Levene residuals as a powerful approach to detect scale differences between several groups. The proposed method is applied to a real data set and also extensive simulation is conducted to assess power and robustness against non-normality.

KW - Multiple contrasts

KW - Heterogeneous variances

KW - Levene residuals

KW - Order-restricted inference

KW - Trend test

UR - http://www.scopus.com/inward/record.url?scp=84912022096&partnerID=8YFLogxK

U2 - 10.1007/s00180-014-0508-z

DO - 10.1007/s00180-014-0508-z

M3 - Article

AN - SCOPUS:84912022096

SN - 0943-4062

VL - 29

SP - 1593

EP - 1608

JO - Computational statistics

JF - Computational statistics

IS - 6

ER -

A Levene-type test of homogeneity of variances against ordered alternatives

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this