时变条件t-copula蒙特卡罗方法的外汇储备收益风险度量  

Measuring Foreign Reserves Portfolio Risk with Time-varying T-copula and Monte Carlo Simulation

作　　者：高岳[1] 王家华[1] 公彦德[1] 

机构地区：[1]南京审计学院金融学院,南京211815

出　　处：《系统管理学报》2012年第3期319-326,共8页Journal of Systems & Management

基　　金：江苏省高校哲学社会科学重点研究基地"金融风险管理研究中心"重大项目(2010JDXM021);江苏省高校自然科学研究计划资助项目(10JHD120001)

摘　　要：在给定我国主要储备货币为美元的基础上,使用英镑、日元、欧元兑美元每日汇率,应用时变条件t-copula函数描述主要储备币种对美元汇率收益序列之间的时变相依结构,建立了用于描述包含时变自由度在内的所有时变相依模型参数的演化方程。采用蒙特卡洛仿真方法计算了各种币种组合的VaR,并对结果进行后验测试,时变条件t-copula函数仿真估计VaR可以覆盖最大损失风险,并分析了主要储备货币组合兑美元汇率风险演化趋势,作为调整外汇储备结构的参考依据。Given the major currency of foreign reserve of China is US dollar, we use the daily exchange rates of Pound Sterling, Japanese Yen and Euro to US dollar to study the risk of foreign reserves. A time-varying t-copula model is used to investigate the dependence between these exchange rates and the evolution equations are developed to describe the time-varying parameters including related correlation coefficient and degree of freedom. Simulated protfolio return series is generated by Monte Carlo method to get VaR of different portfolios. The VaR results are back tested, and the result of these tests shows that VaR series calculated by time-varying T-copula model have a good coverage rate to factual lost. An analysis on the risk trend of these major reserves currency portfolios is also presented. It could be a reference to adjustment of the structure of foreign reserves of China.

关 键 词：时变 COPULA 外汇储备 波动 风险值 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]