Please use this identifier to cite or link to this item:
Title: A modified Bartlett test for linear hypotheses in heteroscedastic one-way ANOVA
Authors: Zhang, J.-T. 
Liu, X.
Keywords: General linear hypothesis testing problem
Heteroscedastic one-way anova
K-Sample Behrens-Fisher Problem
Modified bartlett correction
Issue Date: 2012
Citation: Zhang, J.-T.,Liu, X. (2012). A modified Bartlett test for linear hypotheses in heteroscedastic one-way ANOVA. Statistics and its Interface 5 (2) : 253-262. ScholarBank@NUS Repository.
Abstract: In this paper, we propose and study a so-called modified Bartlett (MB) test for the general linear hypothesis testing (GLHT) problem in heteroscedastic one-way ANOVA. The MB test is easy to compute and implement via using the usual chi-squared distribution. The MB test is shown to be invariant under affine transformations, different choices of the contrast matrix used to define the same hypothesis and different labeling schemes of the population means. Simulation studies demonstrate that the MB test performs well and it outperforms or is comparable to some existing tests for the k-sample Behrens-Fisher problem, a special case of the GLHT problem. The MB test is illustrated using a real data example.
Source Title: Statistics and its Interface
ISSN: 19387989
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Sep 22, 2022

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.