极值理论下的香港汇丰控股VaR实证分析  

VaR Analysis of HSBC Holdings in Hong Kong Based on Extreme Value Theory

作　　者：王晓辉[1] 庄亮亮[1] 

机构地区：[1]华南理工大学理学院,广州510641

出　　处：《科学技术与工程》2011年第16期3858-3860,共3页Science Technology and Engineering

摘　　要：极值理论可以更精确地处理金融数据的厚尾特性。选取香港上市的汇丰控股数据,运用POT方法做实证分析,对时间序列取门限值(Threshold),对超过门限的样本数据建模,极限点渐进分布服从GPD分布,估计模型参数,检验模型的合理性,并给出置信度为95%下的VaR。Extreme value theory can describe the heavy tail characteristics of finance data more exactly.HSBC Holdings in Hong Kong as an example are took,gaven the data analysis by the method of POT as follows： chose the threshold of the data series,modelinged the sample data excess the threshold whose limit converges to the distribution of GPD,estimated parameters,test the reasonability and gave the VAR under 95% confidence level.

关 键 词：GPD分布 阈值模型 POT模型 门限 泊松过程 

分 类 号：F830.9[经济管理—金融学]