×

Extreme smoothing and testing for multivariate normality. (English) Zbl 0955.62060

Summary: Recently, A. W. Bowman and P. J. Foster [J. Am. Stat. Assoc. 88, No. 422, 529–537 (1993; Zbl 0775.62086)] proposed to base a test for multivariate normality on a \(L^2\) distance between a nonparametric kernel density estimator and the parametric density estimator under normality, applied to the empirically standardized data. We show that, for a fixed bandwidth (not depending on the sample size), the test of Bowman and Foster is a member of the class of invariant and universally consistent procedures suggested by N. Henze and B. Zirkler [Commun. Stat., Theory Methods 19, No. 10, 3595–3617 (1990; Zbl 0738.62068)].
Moreover, we identify and study the tests for multivariate normality obtained by letting the bandwidth tend to zero and to infinity. While the former test statistic is based solely on the Euclidean norm of the standardized data, letting the bandwidth tend to infinity yields a weighted sum of K. V. Mardia’s [Biometrika 57, 519–530 (1970; Zbl 0214.46302)] time-honoured measure of multivariate skewness and a sample version of a recently introduced skewness measure of T.F. Móri, V. K. Rohatgi and G. J. Székely [Theory Probab. Appl. 38, No. 3, 547–551 (1993; Zbl 0807.60020)].

MSC:

62H15 Hypothesis testing in multivariate analysis
62G07 Density estimation
Full Text: DOI

References:

[1] Ahn, S. K., \(F\)-probability plot and its application to multivariate normality, Commun. Statist. Theory Meth., 31, 997-1023 (1992) · Zbl 0800.62343
[2] Baringhaus, L.; Henze, N., A consistent test for multivariate normality based on the empirical characteristic function, Metrika, 35, 339-348 (1988) · Zbl 0654.62046
[3] Baringhaus, L.; Henze, N., Limit distributions for Mardia’s measure of multivariate skewness, Ann. Statist., 20, 1889-1902 (1992) · Zbl 0767.62041
[4] Bowman, A. W.; Foster, P. J., Adaptive smoothing and density-based tests of multivariate normality, J. Amer. Statist. Assoc., 88, 529-537 (1993) · Zbl 0775.62086
[5] Csörgő, S., Consistency of some tests for multivariate normality, Metrika, 36, 107-116 (1989) · Zbl 0705.62053
[6] Epps, T. W.; Pulley, L. B., A test for normality based on the empirical characteristic function, Biometrika, 70, 723-726 (1983) · Zbl 0523.62045
[7] Fang, K. T.; Kotz, S.; Ng, K. W., Symmetric Multivariate and Related Distributions (1989), Chapman & Hall: Chapman & Hall London
[8] Henze, N.; Zirkler, B., A class of invariant and consistent tests for multivariate normality, Commun. Statist. Theory Meth., 19, 3595-3617 (1990) · Zbl 0738.62068
[9] Henze, N., On Mardia’s kurtosis test for multivariate normality, Commun. Statist. Theory Meth., 23, 1031-1045 (1994) · Zbl 0825.62136
[10] Henze, N., Limit laws for multivariate skewness in the sense of Móri, Rohatgi and Székely, Statist. Probab. Lett. (1996), to appear · Zbl 0902.62060
[11] Henze, N.; Wagner, Th., A new approach to the BEHP class of tests for multivariate normality, J. Multivar. Anal. (1996), to appear
[12] Horswell, R. L.; Looney, St. W., A comparison of tests for multivariate normality that are based on measures of multivariate skewness and kurtosis, J. Statist. Comput. Simulations, 42, 21-38 (1992)
[13] Kariya, T.; George, E., Locally best invariant tests for multivariate normality in curved families with μ known, IMS Lecture Notes, Monograph Series, 24, 311-322 (1992)
[14] Koziol, J. A., A class of invariant procedures for assessing multivariate normality, Biometrika, 69, 423-427 (1982) · Zbl 0494.62027
[15] Koziol, J. A., Probability plots for assessing multivariate normality, The Statistician, 42, 161-173 (1993)
[16] Mardia, K. V., Measures of multivariate skewness and kurtosis with applications, Biometrika, 57, 519-530 (1970) · Zbl 0214.46302
[17] Móri, T. F.; Rohatgi, V. K.; Székely, G. J., On multivariate skewness and kurtosis, Theory Probab. Appl., 38, 547-551 (1993) · Zbl 0807.60020
[18] Mudholkar, G. S.; Mc Dermott, M.; Srivastava, D. K., A test of \(p\)-variate normality, Biometrika, 79, 850-854 (1992) · Zbl 0850.62428
[19] Mudholkar, G. S.; Srivastava, D. K.; Lin, C. Th., Some \(p\)-variate adaptions of the Shapiro-Wilk test of normality, Commun. Statist. Theory Meth., 24, 953-985 (1995) · Zbl 0825.62319
[20] Naito, K., On weighting the studentized empirical characteristic function for testing normality, Commun. Statist. Simulations, 25, 201-213 (1996) · Zbl 0875.62226
[21] Ozturk, A.; Romeu, J. L., A new method for assessing multivariate normality with graphical applications, Commun. Statist. Simulations, 21, 15-34 (1992) · Zbl 0850.62432
[22] Paulson, A. S.; Roohan, P.; Sullo, P., Some empirical distribution function tests for multivariate normality, J. Statist. Comput. Simulations, 28, 15-30 (1987) · Zbl 0619.62049
[23] Rayner, J. C.W.; Best, D. J.; Matthews, K. L., Interpreting the skewness coefficient, Commun. Statist. Theory Meth., 24, 593-600 (1995) · Zbl 0825.62298
[24] Romeu, J. L.; Ozturk, A., A comparative study of goodness-of-fit tests for multivariate normality, J. Multivar. Anal., 46, 309-334 (1993) · Zbl 0778.62051
[25] Singh, A., Omnibus robust procedures for assessment of multivariate normality and detection of multivariate outliers, (Patil, G. P.; Rao, C. R., Multivariate Environmental Statistics (1993), North-Holland: North-Holland Amsterdam), 445-488 · Zbl 0825.62492
[26] Versluis, C., Comparison of tests for bivariate normality with unknown parameters by transformation to an univariate statistic, Commun. Statist. Theory Meth., 25, 647-665 (1996) · Zbl 0875.62233
[27] Viollaz, A. J., Convergence in weigthed supremum norms of the Skorokhod representation of the estimated empirical process, Commun. Statist. Theory Meth., 24, 2829-2839 (1995) · Zbl 0875.62194
[28] Zhu, L.; Wong, H. L.; Fang, K. T., A test for multivariate normality based on sample entropy and projection pursuit, J. Statist. Plann. Inference, 45, 373-385 (1995) · Zbl 0822.62050
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.