基于GARCH-VaR模型的汇率风险实证研究  

Empirical Research on Exchange Rate Risk Based on GARCH-VaR Model

作　　者：杨彬彬[1] 徐庆娟[1] 

机构地区：[1]广西师范学院数学与统计科学学院,广西南宁530023

出　　处：《广西师范学院学报（自然科学版）》2017年第1期32-39,共8页Journal of Guangxi Teachers Education University(Natural Science Edition)

基　　金：混合与缺失数据统计分析广西高校重点实验室科学基金开放项目(GXMMSL201407);广西高校科学技术研究项目(KY2015YB1230)

摘　　要：现阶段人民币汇率波动及其风险度量受到广泛关注.该文基于2013年1月4日至2016年12月5日美元、欧元、加元和港币的人民币汇率每日中间价数据,建立t分布和广义误差(GED)分布下的广义自回归条件异方差(GARCH)模型,并在此基础上计算四个汇率收益率序列的VaR值.最后,通过似然比(LR)方法检验VaR值的有效性,得出99%置信度下GARCH-GED模型计算的VaR值准确性较高.At the present stage, the volatility and risk measurement of RMB exchange rate have attracted wide attention. In this paper, based on the data of exchange rate daily price of USD/CNY, EUR/CNY, CAD/CNY and HKD/CNY from January 4th, 2013 to December 5th, 2016, we establish GARCH models based on t-distribution and generalized error distribution （GED）, respectively. On this basis, we estimate the value of VaR of four exchange rate series. Finally, the validity of the above VaR series is tested by the likelihood ratio （LR） test. The results show that GARCHGARCH; VaR; exchange rate risk GED model has a higher accuracy under the confidence of 99%.

关 键 词：GARCH VAR 汇率风险 

分 类 号：F830.92[经济管理—金融学]