基于Copula函数的金融时间序列模型述评  

A Review on Copula-based Financial Time Series Models

作　　者：张超锋[1,2] 张莉敏[2] 

机构地区：[1]对外经济贸易大学国际经济贸易学院,北京100029 [2]四川文理学院数学与财经学院,四川达州635000

出　　处：《统计与信息论坛》2014年第4期3-9,共7页Journal of Statistics and Information

基　　金：四川省自然科学基金项目<转型期股市投资组合风险度量建模与实证研究>(13ZB0102)

摘　　要：结合当前Copula函数及其应用的热点问题,着重评述了基于Copula函数的金融时间序列模型的应用。鉴于利用Copula可以将边际分布和变量间的相依结构分开来研究这一优良性质,在设定和估计模型时便显得极为方便和灵活。从模型的构造、Copula函数的选择、模型的估计以及拟合优度检验等几方面展开阐述和评价,介绍了Copula模型在金融领域中的几类应用,并对Copula理论和应用的新视角进行了展望。This survey reviews the large and growing literature on Copula-based models for financial time series. Copula-based models have a very flexible property that they allow the researcher to specify the models for the marginal distributions separately from the dependence structure. This makes specifying and estimating the models more convenient and easier. The construction of the time series models, the choice of Copula function and inference methods as well as good-of-fit tests are reviewed. The last part is some applications of these Copulas for financial time series.

关 键 词：COPULA函数 相依结构 金融时间序列 

分 类 号：F830.9[经济管理—金融学] O212[理学—概率论与数理统计]