中文摘要：

运用Copula—ASV—GPD模型对我国多元外汇储币组合进行风险研究。首先针对外汇收益的尖峰厚尾、波动的异方差性等典型事实特征，采用ASV模型与极值理论结合刻画单个外汇收益的波动性及尾部分布。然后运用更为灵活的tCopula函数进行拟合多元外汇储币组合的相关结构，最后结合Monte Carlo模拟对外汇组合进行了风险度量。通过对外汇储币组合的实证分析，结果表明，基于ASV～GPD的边缘分布模型能有效地刻画多元外汇收益时序并较为精确地描述外汇收益尾部的极端变化，相比其他风险度量模型具有优越性。同时，回测检验显示，基于Copula—ASV—GPD模型的多元外汇组合对风险测度能力更强，能够更好地捕捉外汇组合极端情形下的协同性和关联性，因而能有效地管理外汇储币风险。

英文摘要：

The purpose of this paper is to study the multiple foreign exchange reserve in China by using Copula-ASV-GPD model. Based on the characteristic of fat tail, fluctution heteroscedasticity and nonlinear correlation of the combination of multiple foreign exchange reserve portfolio, this paper combines the ASV models with the EVT to depict the single exchange rate asset return volatility and tail characteristics, apply t Copula function to treat with the non-linear structures among assets and combine with Monte Carlo simulation the risk of portfolio is measured. By empirical analysis of the multiple foreign exchange reserve, it is found that the ASV-GPD model could effectively depict the time series of return for financial assets and accurately treat abnormal changes of the tail, and the method based on Copula Function and ASV-GPD model to measure portfolio risk can manage effectively risk. Moreover, the backtesting results show that the model is suitable for measurement of tail dependence risk of the multiple foreign exchange reserve.