On distribution-free tests for the multivariate two-sample location-scale model. (English) Zbl 1010.62035

Summary: We propose simple exact procedures for testing both a location shift and/or a scale change between two multivariate distributions. Our tests are strictly distribution-free and can be made either scale invariant or rotation invariant. Our approach combines a generalization of the Wilcoxon test based on projections of the data onto the first principal component, a generalization of the Siegel-Tukey test based on the concept of data depth, and a bivariate test for the location problem proposed by K.V. Mardia [J. R. Stat. Soc., Ser. B 29, 320-342 (1967; Zbl 0157.48004)]. In addition, we show that the limiting null distribution of a test statistic proposed by R.Y. Liu and K. Singh [J. Am. Stat. Assoc. 88, No. 421, 252-260 (1993; Zbl 0772.62031)] does not depend on the depth considered.


62G10 Nonparametric hypothesis testing
62H15 Hypothesis testing in multivariate analysis
62H25 Factor analysis and principal components; correspondence analysis
Full Text: DOI


[1] Brown, B. M.; Hettmansperger, T. P., Affine invariant rank methods in the bivariate location model, J. Roy. Statist. Soc. Ser. B, 49, 301-310 (1987) · Zbl 0653.62039
[2] Chatterjee, S. K.; Sen, P. K., Nonparametric tests for the bivariate two sample location problem, Calcutta Statist. Assoc. Bull., 13, 18-58 (1964) · Zbl 0129.32801
[3] Gibbons, J. D., Nonparametric Methods for Quantitative Analysis (1976), Holt, Rienehart and Winston: Holt, Rienehart and Winston New York · Zbl 0369.62049
[4] Hand, D. J.; Daly, F.; Lunn, A. D.; McConway, K. J.; Ostrowski, E., A Handbook of Small Data Sets (1994), Chapman and Hall: Chapman and Hall London · Zbl 0949.62500
[5] Hettmansperger, T. P., Statistical Inference Based on Ranks (1984), Wiley: Wiley New York · Zbl 0592.62031
[6] Liu, R. Y., On a notion of data depth based on random simplices, Ann. Statist., 18, 405-414 (1990) · Zbl 0701.62063
[7] Liu, R. Y.; Singh, K., A quality index based on data depth and multivariate rank tests, J. Amer. Statist. Assoc., 88, 252-260 (1993) · Zbl 0772.62031
[8] Liu, R. Y., Control charts for multivariate processes, J. Amer. Statist. Assoc., 90, 1380-1387 (1995) · Zbl 0868.62075
[9] Mardia, K. V., A non-parametric test for the bivariate two-sample location problem, J. Roy. Statist. Soc. Ser. B, 29, 320-342 (1967) · Zbl 0157.48004
[10] Morant, G. M., A first study of the Tibetan skull, Biometrika, 14, 193-260 (1923)
[11] Oja, H., Descriptive statistics for multivariate distribution, Statist. Probab. Lett., 1, 327-333 (1983) · Zbl 0517.62051
[12] Peters, D.; Randles, R. H., A bivariate signed rank test for the two-sample location problem, J. Roy. Statist. Soc. Ser. B, 53, 493-504 (1991) · Zbl 0800.62252
[13] Puri, M. L.; Sen, P. K., On a class of multivariate multisample rank-order tests, Sankhyā Ser. A, 28, 353-375 (1966) · Zbl 0156.39902
[14] Puri, M. L.; Sen, P. K., Nonparametric Methods in Multivariate Analysis (1971), Wiley: Wiley New York · Zbl 0237.62033
[15] Randles, R. H., A two sample extension of the multivariate interdirection sign test, (Dodge, Y., \(L_1\)-Statistical Analysis and Related Methods (1992), North-Holland: North-Holland Amsterdam), 295-302
[16] Randles, R. H.; Peters, D., Multivariate rank tests for the two-sample location problem, Commun. Statist. Theory Methods, 19, 4225-4238 (1992)
[17] Tamura, R., Multivariate nonparametric several-sample tests, Ann. Math. Statist., 37, 611-618 (1966) · Zbl 0151.23602
[18] Tukey, J. W., Mathematics and picturing data, Proc. of the 1974 International Congress of Mathematicians, Vancouver (1975), p. 523-531 · Zbl 0347.62002
[19] Vincze, I., On two-sample tests based on order statistics, Proc. 4th Berkeley Symp. Math. Statist. and Probab. (1961), p. 695-705 · Zbl 0121.36303
[20] Wald, A.; Wolfowitz, J., Statistical tests based on permutation of observations, Ann. Math. Statist., 15, 358-372 (1944) · Zbl 0063.08124
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.