Conditional Dependence Modellingwith Regular Vine Copulas

Abstract

Modelling sophisticated high-dimensional dependence structures forfinancial assets in a portfolio framework require flexible dependencemodels. In this paper, a regular vine-copula based model is employed toanalyze financial dependencies and co-movements of a six-dimensionalportfolio of currency exchange rates starting from January 2001 to April2018. The regular-vine copula based model employs partial correlationsto construct the regular vine structure and offer superior flexibility inthe selection of the distributions to model financial dependence struc-ture. The model also captures the asymmetry between multivariatevariables using bivariate copulas with flexible tail dependence. Empiri-cal evidence suggests that co-movements in currency markets are mostlikely to experience a crash and boom together thus, concluding thatcurrency markets are integrated due to the nature of the global finan-cial systems. The C-Vine copula specification is favoured over the other copula specifications in modeling the dependence dynamics between cur-rency exchange rates.