Model-based clustering with R-vine copulas

Finite mixtures are applied to perform model-based clustering of multivariate data. Existing models are not exible enough for modeling the dependence of multivariate data since they rely on potentially undesirable correlation restrictions to be computationally tractable. We discuss a model-based clustering method via R-vine copula to understand the complex and hidden dependence patterns in correlated multivariate data. One of the advantages of this approach is that it accounts for the tail asymmetry of the data by using blocks of asymmetric bivariate copulas. We use real datasets to illustrate the proposed procedure.