Finite normal mixture copulas for multivariate discrete data modeling

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

A new family of copulas is introduced that provides flexible dependence structure while being tractable and simple to use for multivariate discrete data modeling. The construction exploits finite mixtures of uncorrelated normal distributions. Accordingly, the cumulative distribution function is simply the product of univariate normal distributions. At the same time, however, the mixing operation introduces association. The properties of the new family of copulas are examined and a concrete application is used to show its applicability.
Original languageEnglish
Pages (from-to)3878-3890
Number of pages13
JournalJournal of Statistical Planning and Inference
Volume139
Issue number11
DOIs
Publication statusPublished - 1 Nov 2009

Cite this