Statistical significance levels of nonparametric tests biased by heterogeneous variances of treatment groups

Authors
Citation
Dw. Zimmerman, Statistical significance levels of nonparametric tests biased by heterogeneous variances of treatment groups, J GEN PSYCH, 127(4), 2000, pp. 354-364
Citations number
18
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Psycology
Journal title
JOURNAL OF GENERAL PSYCHOLOGY
ISSN journal
0022-1309 → ACNP
Volume
127
Issue
4
Year of publication
2000
Pages
354 - 364
Database
ISI
SICI code
0022-1309(200010)127:4<354:SSLONT>2.0.ZU;2-S
Abstract
The statistical significance levels of the Wilcoxon-Mann-Whitney test and t he Kruskal-Wallis test are substantially biased by heterogeneous variances of treatment groups-even when sample sizes are equal. Under these condition s, the Type I error probabilities of the nonparametric tests, performed at the .01, .05, and .10 significance levels, increase by as much as 40%-50% i n many cases and sometimes as much as 300%. The bias increases systematical ly as the ratio of standard deviations of treatment groups increases and re mains fairly constant for various sample sizes. There is no indication that Type I error probabilities approach the significance level asymptotically as sample size increases.