A test for multivariate skew-normality based on its canonical form

JOURNAL OF MULTIVARIATE ANALYSIS

卷:128

Article

Balakrishnan, N.^1,4  Capitanio, A.²  Scarpa, B.³ 

[1] McMaster Univ, Dept Math & Stat, Hamilton, ON, Canada

[2] Univ Bologna, Dept Stat Sci, Bologna, Italy

[3] Univ Padua, Dept Stat Sci, Padua, Italy

[4] King Abdulaziz Univ, Dept Stat, Jeddah 21413, Saudi Arabia

关键词: Multivariate skewness;    Skew-normal distribution;    Canonical form;    Order statistics;   

DOI  :  10.1016/j.jmva.2014.02.015

来源: Elsevier

【 摘 要 】

A test to assess if a sample comes from a multivariate skew-normal distribution is proposed. The test statistic is obtained from the canonical form of the multivariate skew-normal distribution and its null distribution is derived. The power of the proposed test is evaluated through Monte Carlo simulations for different conveniently chosen alternatives. Finally, three numerical examples are presented for the purpose of illustration. (C) 2014 Elsevier Inc. All rights reserved.

【 授权许可】

Free