摘要
在险价值(VaR)是度量市场风险的普遍工具,可看作是市场风险度量的基石.在估计资产尾部的VaR时,极值方法比传统方法更具优势.但是,一般的极值模型都假定数据是独立同分布的,而大多金融数据具有局部相关性,并不满足模型的条件.笔者利用分串的方法处理上证指数的数据,得到了较好的结果.
Value-at-Risk （VaR） is a commonly used tool to measure the market risk, and also the benchmark in the risk management. The extreme value theory has more advantages than traditional tools in estimating the VaR of the tail of an asset. The general extreme value models suppose that the data are independent and have the identical distribution. However, most of financial dada are local dependent, so they do not meet the model conditions. The data of VaR of Shanghai index are estimated by using the method of declustering, and the result is vety good.
出处
《天津城市建设学院学报》
CAS
2005年第3期217-219,共3页
Journal of Tianjin Institute of Urban Construction
关键词
上证指数
在险价值
极值理论
分串
Shanghai index
value-at-risk （VaR）
extreme value theory
declustering
