论文信息 - A graphical method for assessing multivariate normality

A graphical method for assessing multivariate normality

SummaryIn this paper we suggest a simple graphical device for assessing multivariate normality. The method is based on the characteristic that linear combinations of the sample mean and sample covariance matrix are independent if and only if the random variable is normally distributed. We demonstrate the usage of the suggested method and compare it to the classical Q-Q plot by using some multivariate data sets.

H. E. Holgersson | H. Holgersson

[1] J. Shao,et al. The jackknife and bootstrap , 1996 .

[2] A. Azzalini,et al. The multivariate skew-normal distribution , 1996 .

[3] R. Koenker,et al. Robust Tests for Heteroscedasticity Based on Regression Quantiles , 1982 .

[4] Eugene Lukacs,et al. A Characterization of the Normal Distribution , 1942 .

[5] K. Mardia. 9 Tests of unvariate and multivariate normality , 1980 .

[6] A. Azzalini. A class of distributions which includes the normal ones , 1985 .

[7] Robert Tibshirani,et al. An Introduction to the Bootstrap , 1994 .