FEB Research Report KBI_1519
Publication date:
2015-01-01
Publisher:
KU Leuven - Faculty of Economics and Business; Leuven (Belgium)
Author:
Pircalabelu, Eugen
Claeskens, Gerda ; Gijbels, Irène
Keywords:
Directed acyclic graph, Copula, C-vine, D-vine, Model selection
Abstract:
A new methodology for selecting a Bayesian network for continuous data outside the widely used class of multivariate normal distributions is developed. The ‘copula DAGs’ combine directed acyclic graphs and their associated probability models with copula C/D-vines. Bivariate copula densities introduce flexibility in the joint distributions of pairs of nodes in the network. An information criterion is studied for graph selection tailored to the joint modeling of data based on graphs and copulas. Examples and simulation studies show the flexibility and properties of the method.