Bartlett's, Cochran's, and Hartley's Tests on Variances are Liberal When the Underlying Distribution is Long-Tailed
作者:
Louis-Paul Rivest,
期刊:
Journal of the American Statistical Association
(Taylor Available online 1986)
卷期:
Volume 81,
issue 393
页码: 124-128
ISSN:0162-1459
年代: 1986
DOI:10.1080/01621459.1986.10478248
出版商: Taylor & Francis Group
关键词: Majorization;Normal mixture;Schur convexity;Star-shaped ordering;X2distribution
数据来源: Taylor
摘要:
For samples of equal size, thepvalues of Bartlett's, Cochran's, and Hartley's tests for the equality of several variances, obtained under the normality assumption, are shown to underestimate the truepvalues when the parent distribution is a normal or aX21scale mixture or when there is within-sample dependence. The proof uses elements of majorization theory. When the sample sizes are not equal, a partial extension is obtained for the two-sample case.
点击下载:
PDF (435KB)
返 回