对数收益率的偏斜Logistic分布与VaR估计  

The Skew Logistic Distribution of Log Return Rate and the Estimation of VaR

作　　者：杨昕[1] 

机构地区：[1]广西财经学院国际教育中心,广西南宁530003

出　　处：《数理统计与管理》2011年第3期548-553,共6页Journal of Applied Statistics and Management

基　　金：国家自然科学基金(11061007);广西自然科学基金(2011GXNSFA018133)

摘　　要：本文通过直方图和Q-Q图的直观方法展示了上证指数和深证指数的对数收益率具有尖峰厚尾和偏斜的分布特征,利用Shapiro-Wilk正态性检验和Kolmogorov-Smirnov检验等方法检验了对数收益率的分布与正态分布有显著性差异,并以较大的概率水平接受了对数收益率服从偏斜Logistic分布,同时给出了基于偏斜Logistic分布的VaR风险量的估计,结果显示上证指数的风险小于深证指数的风险。By the visual methods of histogram and Q-Q plot,this paper illustrates the distribution characteristics of excess kurtosis,heavy-tail and skew for the log return rates of the two stock market indies of Shangzheng and Shenzheng.The distributions of the log return rates have very significant different from normal distribution by the Shapiro-Wilk test and Kolmogorov-Smirnov test,and the skew Logistic distribution is accepted with very large probability.At the same time,the estimation of VaR based on the skew Logistic distribution is given.The results report that the risk of the Shangzheng index is lower than that of the Shenzheng index.

关 键 词：对数收益率 偏斜Logistic分布 尖峰厚尾 非对称 风险量 

分 类 号：F830.91[经济管理—金融学] F224.9