Sequential Bayesian Model Selection of Regular Vine Copulas

TL;DR

This paper introduces a Bayesian approach for selecting regular vine copula models, allowing flexible pair family choices and including the vine structure in the inference process, demonstrated through simulations and real data applications.

Contribution

It extends Bayesian family selection to arbitrary candidate sets and incorporates vine structure inference into the model selection process.

Findings

Outperforms existing methods in simulation benchmarks

Effective in portfolio risk measurement applications

Flexible family selection enhances modeling accuracy

Abstract

Regular vine copulas can describe a wider array of dependency patterns than the multivariate Gaussian copula or the multivariate Student's t copula. This paper presents two contributions related to model selection of regular vine copulas. First, our pair copula family selection procedure extends existing Bayesian family selection methods by allowing pair families to be chosen from an arbitrary set of candidate families. Second, our method represents the first Bayesian model selection approach to include the regular vine density construction in its scope of inference. The merits of our approach are established in a simulation study that benchmarks against methods suggested in current literature. A real data example about forecasting of portfolio asset returns for risk measurement and investment allocation illustrates the viability and relevance of the proposed scheme.