A Bayesian Semiparametric Gaussian Copula Approach to a Multivariate\n Normality Test

2019/07/03 by Luai Al‐Labadi, Al-Labadi, Luai, Forough Fazeli Asl +3
Computer Science · Economics, Econometrics and Finance · Mathematics · #62F15 #62G10 #62H15 #Applications (stat.AP) #Bayesian Methods and Mixture Models #Computation (stat.CO) #FOS: Computer and information sciences #Financial Risk and Volatility Modeling #Methodology (stat.ME) #Statistical Distribution Estimation and Applications

paper · pdf · doi:10.48550/arxiv.1907.01736

openalex publication_date 2019/07/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, a Bayesian semiparametric copula approach is used to model the\nunderlying multivariate distribution F_true. First, the Dirichlet process\nis constructed on the unknown marginal distributions of F_true. Then a\nGaussian copula model is utilized to capture the dependence structure of\nF_true. As a result, a Bayesian multivariate normality test is developed by\ncombining the relative belief ratio and the Energy distance. Several\ninteresting theoretical results of the approach are derived. Finally, through\nseveral simulated examples and a real data set, the proposed approach reveals\nexcellent performance.\n

Related

• A Bayesian Nonparametric Test for Assessing Multivariate Normality
• Multivariate Normality Test with Copula Entropy
• Approximate Bayesian inference in semiparametric copula models
• An Effective Multivariate Normality Test via Hessians of Empirical Cumulant Generating Functions
• A Normality Test for Multivariate Dependent Samples