基于EVT-BM-FIGARCH的动态VaR风险测度  

Dynamic VaR Risk Measures Based on EVT-BM-FIGARCH

作　　者：肖智[1] 傅肖肖[1] 钟波[2] 

机构地区：[1]重庆大学经济与工商管理学院,重庆400030 [2]重庆大学数理学院,重庆400030

出　　处：《中国管理科学》2008年第4期18-23,共6页Chinese Journal of Management Science

摘　　要：对金融资产回报,用FIGARCH模型捕捉波动的异方差性和长期记忆性的同时,将回报序列转化为标准残差序列、通过用EVT-BM方法拟合标准残差的尾部分布来处理回报序列的厚尾性,建立了金融风险度量模型——基于EVT-BM-FIGARCH的动态VaR模型。并用该模型对上证综合指数进行实证分析,结果表明模型能够更精确、合理地度量上证综合指数回报的VaR风险。This article uses FIGARCH model to handle the heteroscedasticity and long memory behavior in return＇s volatility. At the same time, it transfers return series into standard residuals and uses EVT-BM method to capture the fat tails of standard residuals. Thus it deals with return＇s fat-tails trait in this way. Then, the paper constructs a dynamic VaR risk measure based on EVT-BM- FIGARCH and applies it to daily returns of composite index of Shanghai stock market. The empirical analysis indicates that the risk measure can describe the index return＇s dynamic VaR risk more exactly and reasonably.

关 键 词：EVT-BM FIGARCH 厚尾 长期记忆 VAR 

分 类 号：F224[经济管理—国民经济]