A new exact p-value approach for testing variance homogeneity

To test variance homogeneity, various likelihood-ratio based tests such as the Bartlett's test have been proposed. The null distributions of these tests were generally derived asymptotically or approximately. We re-examine the restrictive maximum likelihood ratio (RELR) statistic, and suggest a...

Full description

Bibliographic Details
Main Authors: Juan Wang, Xinmin Li, Hua Liang
Format: Article
Language:English
Published: Taylor & Francis Group 2022-01-01
Series:Statistical Theory and Related Fields
Subjects:
Online Access:http://dx.doi.org/10.1080/24754269.2021.1907519
_version_ 1797677036845662208
author Juan Wang
Xinmin Li
Hua Liang
author_facet Juan Wang
Xinmin Li
Hua Liang
author_sort Juan Wang
collection DOAJ
description To test variance homogeneity, various likelihood-ratio based tests such as the Bartlett's test have been proposed. The null distributions of these tests were generally derived asymptotically or approximately. We re-examine the restrictive maximum likelihood ratio (RELR) statistic, and suggest a Monte Carlo algorithm to compute its exact null distribution, and so its p-value. It is much easier to implement than most existing methods. Simulation studies indicate that the proposed procedure is also superior to its competitors in terms of type I error and powers. We analyse an environmental dataset for an illustration.
first_indexed 2024-03-11T22:39:07Z
format Article
id doaj.art-c531a484506849b89de3c2fbdccef5f3
institution Directory Open Access Journal
issn 2475-4269
2475-4277
language English
last_indexed 2024-03-11T22:39:07Z
publishDate 2022-01-01
publisher Taylor & Francis Group
record_format Article
series Statistical Theory and Related Fields
spelling doaj.art-c531a484506849b89de3c2fbdccef5f32023-09-22T09:19:46ZengTaylor & Francis GroupStatistical Theory and Related Fields2475-42692475-42772022-01-0161818610.1080/24754269.2021.19075191907519A new exact p-value approach for testing variance homogeneityJuan Wang0Xinmin Li1Hua Liang2Qingdao UniversityQingdao UniversityGeorge Washington UniversityTo test variance homogeneity, various likelihood-ratio based tests such as the Bartlett's test have been proposed. The null distributions of these tests were generally derived asymptotically or approximately. We re-examine the restrictive maximum likelihood ratio (RELR) statistic, and suggest a Monte Carlo algorithm to compute its exact null distribution, and so its p-value. It is much easier to implement than most existing methods. Simulation studies indicate that the proposed procedure is also superior to its competitors in terms of type I error and powers. We analyse an environmental dataset for an illustration.http://dx.doi.org/10.1080/24754269.2021.1907519homogeneity of variancesbartlett's testrestrictive maximum likelihood ratio testtype i error rate
spellingShingle Juan Wang
Xinmin Li
Hua Liang
A new exact p-value approach for testing variance homogeneity
Statistical Theory and Related Fields
homogeneity of variances
bartlett's test
restrictive maximum likelihood ratio test
type i error rate
title A new exact p-value approach for testing variance homogeneity
title_full A new exact p-value approach for testing variance homogeneity
title_fullStr A new exact p-value approach for testing variance homogeneity
title_full_unstemmed A new exact p-value approach for testing variance homogeneity
title_short A new exact p-value approach for testing variance homogeneity
title_sort new exact p value approach for testing variance homogeneity
topic homogeneity of variances
bartlett's test
restrictive maximum likelihood ratio test
type i error rate
url http://dx.doi.org/10.1080/24754269.2021.1907519
work_keys_str_mv AT juanwang anewexactpvalueapproachfortestingvariancehomogeneity
AT xinminli anewexactpvalueapproachfortestingvariancehomogeneity
AT hualiang anewexactpvalueapproachfortestingvariancehomogeneity
AT juanwang newexactpvalueapproachfortestingvariancehomogeneity
AT xinminli newexactpvalueapproachfortestingvariancehomogeneity
AT hualiang newexactpvalueapproachfortestingvariancehomogeneity