Copula Based Multivariate Statistical Model using WinBUGS

Copula Based Multivariate Statistical Model using WinBUGS

Multivariate probability models, where normal distributions fail to provide an adequate approximation, can be constructed by employing the copula functions. Copula functions have emerged in mathematical finance. statistics, extreme value theory and risk management as an alternative approach for modeling multivariate dependence. The International Actuarial Association recommends using copulas for modeling dependence in insurance portfolios. Copulas are now standard tools in credit risk management. Any multivariate distribution can be expressed as a copula function evaluated at each of the marginal distributions. WinBUGS is a window based program with its ability to fit complex statistical models asing Bayesian inference approach and MCAIC algorithms. In this paper, we discuss implementation of the WinBUGS programs in fitting the copula models using Iranʹs light oil prices and export data.