Asymmetric GARCH Value at Risk of GOLD

• Main Authors: Yi-Ting Chen, 陳翊庭
• Other Authors: YONG-CHENG SU
• Format: Others
• Language: en_US
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/19794477984792104496

碩士 === 國立臺灣大學 === 財務金融學研究所 === 102 === VaR is more applicable as a financial management tool to control risk. Since the GARCH model is proved to be the useful and more accurate model in estimating VaR, in this paper, we employ the asymmetric GARCH models including the innovation-rotated GJR GARCH and the innovation-shifted NA GARCH models with different mean equations in comparison with symmetric GARCHM model to find out a more appropriate GARCH method in estimating VaR of gold price. We gathered the latest 523 daily return of gold and divided into two groups to fit the models and get the VaR estimates under each confidence level we chose. Our major findings are described as follows: (1) In term of violation number, symmetric GARCH model and GJR-GARCH models outperform NA-GARCH models. The result implies that asymmetric GARCH models do not outperform symmetric GARCH models (GARCHM model) all the time. (2) We evidently find out ARMA(1,1)-NA-GARCHM(1,1) is the best fitted model in estimating VaR of gold price through forward test among GARCH models with four types of mean equations. (3) The relatively smaller asymmetric effect of NA-GARCH models (ARMA(1,1)-NA-GARCHM(1,1)) fits better with the relatively stable character of gold price compared to GJR-GARCH models.