Modeling Dependent Financial Assets By Dynamic Copula And Portfolio Optimization Based On Cvar

Abstract

This paper is concerned with the statistical modeling of the dependence structure of multivariate financial data using copula. Since financial data is greatly affected by the economic factors, it often varies according to the time. Therefore, dynamic copula model is used that takes into account the time-varying. In addition, portfolio optimization based on Mean-CVaR model is applied with Monte Carlo simulation. As an application, a portfolio with four different Indexes is constructed from the Turkish financial markets. The marginal distributions of assets in the portfolio are estimated and parameter estimates are given for the different copula models. The portfolio optimization based on CVaR is made for the portfolio created from the specified copula model.