Apply Copula Function in the Evaluation of Dependence and VaR for BRICS Portfolios

• Main Authors: Tai-Yuan Huang, 黃泰源
• Other Authors: Wo-Chiang Lee
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/56792271128368156348

碩士 === 淡江大學 === 財務金融學系碩士班 === 101 === The study applies VAR-COV, CCC, DCC, and Copula based GJR-GARCH Model to evaluate Value at Risk for portfolios of BRICS. To refer to procedure Huang et al. (2009) proposed. On the other hand, the study applies Likelihood Ratio Test which Kupiec (1995) proposed and penetration ratio to evaluate the accuracy of VaR model. The empirical results demonstrate the relationship between BRICS index has significant increasing that didn’t have diversified effect of risk. By likelihood ratio test, Copula based GJR-GARCH model can correctly forecast 99 percentage VaR but VAR-COV, CCC, DCC model can’t forecast VaR rationally after Greek government debt crisis. Compared with traditional linear structure, nonlinear structure are relatively correct on VaR forecasting. Finally, consider full sample estimated Student''s t Copula and SJC Copula have significantly effect to fitting the relationship between portfolios of BRICS VaR but the others haven’t.