基于Generalized-Hyperbolic分布的VaR和CVaR拟合实证研究  

An empirical study on Generalized-Hyperbolic distribution based VaR and CVaR estimation

作　　者：张亮亮 杨青[2] 熊国兵 

机构地区：[1]光大证券风险管理部,上海200040 [2]复旦大学经济学院,上海200433

出　　处：《郑州轻工业学院学报（自然科学版）》2011年第5期121-124,共4页Journal of Zhengzhou University of Light Industry:Natural Science

基　　金：国家自然科学基金项目(70702028);上海浦江人才计划资助项目

摘　　要：基于Generalized-Hyperbolic分布模型,采用极大似然方法,利用中国市场数据对VaR和CVaR进行了动态拟合、实证结果以及模型的后测检验.结果表明:使用Generalized-Hyperbolic分布比使用正态分布可以有效地降低VaR计算失败的次数,且置信度越高其拟合效果越好,是一种很好的静态VaR,CVaR估计方法.The VaR and CVaR model were calibrated using Chinese market data based on Generalized-Hyperbolic distribution and with maximum likelihood method,the empirical and back testing results are presented.The results showed that the introduction of G-H distribution effectivly reduced the failure rate of VaR model,and the higher the percentile,the better the fit result is.It is thus proved that G-H parametric method is a very good VaR and CVaR estimation technique.

关 键 词：Generalized-Hyperbolic分布 VAR CVAR 拟合 

分 类 号：O186.12[理学—数学]