The Kruskal-Wallis Test and Stochastic Homogeneity

Journal of Educational and Behavioral Statistics - Tập 23 Số 2 - Trang 170-192 - 1998
András Vargha1, Harold D. Delaney2
1Eötvös Loránd University
2University of New Mexico

Tóm tắt

For the comparison of more than two independent samples the Kruskal-Wallis H test is a preferred procedure in many situations. However, the exact null and alternative hypotheses, as well as the assumptions of this test, do not seem to be very clear among behavioral scientists. This article attempts to bring some order to the inconsistent, sometimes controversial treatments of the Kruskal-Wallis test. First we clarify that the H test cannot detect with consistently increasing power any alternative hypothesis other than exceptions to stochastic homogeneity. It is then shown by a mathematical derivation that stochastic homogeneity is equivalent to the equality of the expected values of the rank sample means. This finding implies that the null hypothesis of stochastic homogeneity can be tested by an ANOVA performed on the rank transforms, which is essentially equivalent to doing a Kruskal-Wallis H test. If the variance homogeneity condition does not hold then it is suggested that robust ANOVA alternatives performed on ranks be used for testing stochastic homogeneity. Generalizations are also made with respect to Friedman’s G test.

Từ khóa


Tài liệu tham khảo

Bradley JV, 1968, Distribution-free statistical tests.

10.1080/00401706.1974.10489158

10.3102/10769986007003207

Conover WJ, 1981, The American Statistician, 35, 124

10.1093/biomet/63.3.421

Evans M, 1993, Statistical distributions, 2

Freund JE, 1987, Mathematical statistics, 3

Gibbons JD, 1992, Nonparametric statistical inference, 3

Hájek J, 1969, A course in nonparametric statistics.

10.1016/0167-9473(94)90069-8

Hettmansperger TP, 1984, Statistical inference based on ranks.

Hinkle DE, 1994, Applied statistics for the behavior sciences, 3

10.1214/aoms/1177728261

Howell DC, 1992, Statistical methods for psychology

Hurlburt RT, 1994, Comprehending behavioral statistics

Iman RL, 1994, A data-based approach to statistics.

10.1080/03610927608827446

Jaccard J, 1990, Statistics for the behavioral sciences, 2

10.1093/biomet/38.3-4.324

KendallMGStuartAThe advanced theory of statistics: Vol. 2. Inference and relationship19733rd edLondonGriffin

10.1111/j.2044-8317.1977.tb00742.x

10.1214/aoms/1177729332

10.1080/01621459.1952.10483441

Lehman RS, 1991, Statistics and research in the behavioral sciences.

10.1214/aoms/1177729639

LehmannELNonparametrics: Statistical methods based on ranks1975San FranciscoHolden-Day

10.1214/aoms/1177730491

Maritz JS, 1995, Distribution-free statistical methods, 2

10.1037/0033-2909.97.1.85

MaxwellSEDelaneyHDDesigning experiments and analyzing data: A model comparison perspective1990Belmont, CAWadsworth

10.1037/0033-2909.111.2.361

10.1037/0033-2909.105.1.156

Mosteller F, 1973, Sturdy statistics: Nonparametrics and order statistics

Noether GE, 1967, Elements of nonparametric statistics.

10.1111/j.2044-8317.1992.tb00991.x

Pagano RR, 1994, Understanding statistics in the behavioral sciences, 4

Puri ML, 1985, Nonparametric methods in general linear models

Randles RH, 1979, Introduction to the theory of nonparametric statistics

Runyon RP, 1991, Fundamentals of behavioral statistics, 7

Scheffè H, 1959, The analysis of variance.

Siegel S, 1956, Nonparametric statistics for the behavioral sciences.

10.1016/0167-9473(94)90068-X

Spence JT, 1990, Elementary statistics, 5

Tan WY, 1982, Communications in Statistics—Theory and Methods, 11, 2485

10.1037/0033-2909.99.1.90

Triola MF, 1995, Elementary statistics, 6

Vargha A, 1993, Psychometric methodology: Proceedings of the 7th European Meeting of the Psychometric Society in Trier, 535

10.1093/biomet/38.3-4.330

Welkowitz J, 1991, Introductory statistics for the behavioral sciences, 4

10.3102/10769986012003271

10.1111/j.2044-8317.1988.tb00890.x

10.3102/10769986014003269

10.1111/j.2044-8317.1990.tb00944.x

Wilcox RR, 1996, Statistics for the social sciences.

10.2466/pms.1992.74.3.835