چکیده:
his paper empirically examines the impact of dependence structure between the assets on the portfolio optimization, composed of Tehran Stock Exchange Price Index and Borsa Istanbul 100 Index. In this regard, the method of the Copula family functions is proposed as powerful and flexible tool to determine the structure of dependence. Finally, the impact of the dependence structure on the risk identification and the optimized portfolio selection, will be analyzed. The results show that the t-student copula function provides the best performance among other Copula functions. Also, empirical evidence suggests that the performance of the GJR-Copula-CVaR method is relatively more accurate and more flexible than other common methods of optimization.
خلاصه ماشینی:
GJR-Copula-CVaR Model for Portfolio Optimization: Evidence for Emerging Stock Markets Moien Nikusokhan*1 Received: 2017, June 18 Accepted: 2017, December 4 Abstract his paper empirically examines the impact of dependence structurebetween the assets on the portfolio optimization, composed ofTehran Stock Exchange Price Index and Borsa Istanbul 100 Index.
Patton (2006) applied conditional copula model for determining the joint distribution of daily exchange rates and he found that the dependence structure of exchange rate is asymmetric.
Palaro and Hotta (2006), for eliminated the problem of linear correlation coefficient, identified multivariate distributions of two US stock market index by the conditional copula and showed how conditional copula theory can be a very powerful tool in estimating the portfolio’s Value at Risk (VaR).
So that, the dependence structure between the assets returns that estimated by copula functions, will be replaced linear correlation coefficients.
In the next section, the CVaR GIR-Copula method, including the marginal distribution, dependence structure modeling and the CVaR estimation presented.
is multivariate t- student distribution , � is the correlation −1coefficient, � is the degrees of freedom and �� is the inverse t-studentdistribution; they showed that the t-student copula function expressing the upper and lower tails dependence at the same time.
3. 3 The Dependence Structure Modeling Based on the Copula Functions After estimating the �� marginal distribution, to determine the data dependence structure, normal copula, t-student copula, Klayton, Gumel and Frank functions for portfolios including TEPIX and BIST 100 return couple has been estimated.