A Generalization of Shapiro–Wilk's Test for Multivariate Normality
- 12 May 2009
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 38 (11) , 1870-1883
Abstract
A goodness-of-fit test for multivariate normality is proposed which is based on Shapiro–Wilk's statistic for univariate normality and on an empirical standardization of the observations. The critical values can be approximated by using a transformation of the univariate standard normal distribution. A Monte Carlo study reveals that this test has a better power performance than some of the best known tests for multinormality against a wide range of alternatives.Keywords
This publication has 17 references indexed in Scilit:
- On tests for multivariate normality and associated simulation studiesJournal of Statistical Computation and Simulation, 2007
- A Monte Carlo comparison of the Type I and Type II error rates of tests of multivariate normalityJournal of Statistical Computation and Simulation, 2005
- Invariant tests for multivariate normality: a critical reviewStatistical Papers, 2002
- The Combination Test for Multivariate NormalityJournal of Statistical Computation and Simulation, 2002
- Some p-variate adaptations of the shapiro-wilk test of normalityCommunications in Statistics - Theory and Methods, 1995
- Approximating the Shapiro-Wilk W-test for non-normalityStatistics and Computing, 1992
- A class of invariant consistent tests for multivariate normalityCommunications in Statistics - Theory and Methods, 1990
- An Extension of Shapiro and Wilk's W Test for Normality to Large SamplesJournal of the Royal Statistical Society Series C: Applied Statistics, 1982
- Measures of multivariate skewness and kurtosis with applicationsBiometrika, 1970
- Approximations for the Null Distribution of the W StatisticTechnometrics, 1968