MVN: Multivariate Normality Tests

Assessing the assumption of multivariate normality is required by many parametric multivariate statistical methods, such as discriminant analysis, principal component analysis, MANOVA, etc. Here, we present an R package to asses multivariate normality. The MVN package contains three widely used multivariate normality tests, including Mardia's, Henze-Zirkler's, Royston's, graphical approaches, including chi-square Q-Q plot, perspective plot and contour plot and two outlier detection methods based on Mahalanobis distance. We have also developed web-tool version of the package which is available at http://www.biosoft.hacettepe.edu.tr/MVN/.

Version: 3.5
Depends: R (≥ 2.15.0), nortest, moments, MASS, robustbase, mvoutlier
Imports: methods
Suggests: knitr
Published: 2014-10-15
Author: Selcuk Korkmaz [aut, cre], Dincer Goksuluk [aut]
Maintainer: Selcuk Korkmaz <selcuk.korkmaz at hacettepe.edu.tr>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
URL: http://www.biosoft.hacettepe.edu.tr/MVN/
NeedsCompilation: no
CRAN checks: MVN results

Downloads:

Reference manual: MVN.pdf
Vignettes: Multivariate Normality Tests
Package source: MVN_3.5.tar.gz
Windows binaries: r-devel: MVN_3.5.zip, r-release: MVN_3.5.zip, r-oldrel: MVN_3.5.zip
OS X Snow Leopard binaries: r-release: MVN_3.5.tgz, r-oldrel: MVN_3.5.tgz
OS X Mavericks binaries: r-release: MVN_3.5.tgz
Old sources: MVN archive