Bootstrapping analogs of the one way MANOVA test

Analogs of the classical one way MANOVA model have recently been suggested that do not assume that population covariance matrices are equal or that the error vector distribution is known. These tests are based on the sample mean and sample covariance matrix corresponding to each of the p populations...

Full description

Saved in:
Bibliographic Details
Published inCommunications in statistics. Theory and methods Vol. 48; no. 22; pp. 5546 - 5558
Main Authors Rupasinghe Arachchige Don, Hasthika S., Olive, David J.
Format Journal Article
LanguageEnglish
Published Philadelphia Taylor & Francis 17.11.2019
Taylor & Francis Ltd
Subjects
Analogs
Behrens-Fisher problem
bootstrap
confidence region
coordinatewise median
Covariance matrix
Mathematical analysis
Matrix methods
Outliers (statistics)
Primary 62H15
Regression analysis
Secondary 62G09
Online AccessGet full text

Cover

More Information
Summary:Analogs of the classical one way MANOVA model have recently been suggested that do not assume that population covariance matrices are equal or that the error vector distribution is known. These tests are based on the sample mean and sample covariance matrix corresponding to each of the p populations. We show how to extend these tests using other measures of location such as the trimmed mean or coordinatewise median. These new bootstrap tests can have some outlier resistance, and can perform better than the tests based on the sample mean if the error vector distribution is heavy tailed.
ISSN:0361-0926
1532-415X
DOI:10.1080/03610926.2018.1515363