A Bayesian semiparametric Gaussian copula approach to a multivariate normality test. Issue 3 (11th February 2021)

• Record Type: Journal Article
• Authors: Al-Labadi, Luai; Fazeli Asl, Forough; Saberi, Zahra
• Is Part Of: Journal of statistical computation and simulation. Volume 91:Issue 3(2021)
• Page Start: 543
• Page End: 563
• Publication Date: 2021-02-11
• Subjects: Dirichlet process -- energy distance -- high-dimensional data -- Relative belief inferences -- semiparametric Gaussian copula model; 62F15 -- 62G10 -- 62H15; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5028505
• DOI: 10.1080/00949655.2020.1820504
• Languages: English
• ISSNs: 0094-9655

Abstract

Abstract : Semiparametric copulas are useful tools for modeling a multivariate distribution whose dependence structure is induced by a known copula and whose marginal distributions are estimated. In this paper, a Bayesian semiparametric copula approach is used to model the underlying multivariate distribution F t r u e . First, the Dirichlet process is constructed on the unknown marginal distributions of F t r u e . Then a Gaussian copula model is utilized to capture the dependence structure of F t r u e . As a result, a Bayesian multivariate normality test is developed by combining the relative belief ratio and the Energy distance. Various interesting theoretical results of the approach are derived. Several examples that cover the high dimensional case are discussed to illustrate the approach.