复合极值理论在股市星期效应风险预测中的应用  

Application of Compound Extreme Value Statistical Theory in Risk Forecast of Stock Market Day-of-the-week Effect

作　　者：李月鲜[1] 王海龙[1] LI Yue-xian;WANG Hai-long(College of Science , Inner Mongolia Agricultural University , Hohhot 010020 ,China)

机构地区：[1]内蒙古农业大学理学院

出　　处：《内蒙古大学学报（自然科学版）》2019年第3期240-246,共7页Journal of Inner Mongolia University：Natural Science Edition

基　　金：内蒙古自治区留学回区人员创新启动项目(DC1900004065)

摘　　要：巧妙利用数据破坏了超阀值的成串出现这个特点,又考虑到了每年股市波动程度的不同,使用复合超阀值分布Poisson-GP拟合了上证指数和深圳成指星期一到星期五的尾部分布.采用极大似然估计给出了模型的估计,利用估计结果给出了上证指数和深圳成指星期一到星期五的风险预测.Compound threshold distribution Poisson-GP is applied to fit the tail distribution of the Shanghai Composite Index and Shenzhen Component Index from Monday to Friday by making good use of data to break up the string of overthreshold values and takeing into account the different fluctuations of the stock market each year.Max-Likelihood Estimation is employed to estimate the parameters of model,and Value-at-Risk of Shanghai Composite Index and Shenzhen Component Index from Monday to Friday is given by using the estimated results.

关 键 词：中国股市 VAR 复合超阀值分布 星期效应 

分 类 号：F830[经济管理—金融学]