基于M-Copula-GJRSK-M模型的沪深两市的相依性分析  

Analysis of the Interdependence between Shanghai and Shenzhen Stock Market Based on M-Copula-GJRSK-M Model

作　　者：申建平[1] 孙菲[1] 黄敏[1] 

机构地区：[1]重庆大学数学与统计学院,重庆401331

出　　处：《重庆工商大学学报（社会科学版）》2014年第1期16-21,共6页Journal of Chongqing Technology and Business University：Social Science Edition

摘　　要：金融资产不但存在方差风险,还存在时变偏度风险和时变峰度风险,这使得仅从金融资产的前两阶矩出发来研究风险变化显得十分局限。GJRSK-M模型是描述金融资产的高阶矩风险的有效工具,可对单个金融资产的分布进行拟合,而M-Copula函数能连接组合金融资产的边缘分布,因此本文建立了M-Copula-GJRSK-M模型来研究沪深两股票市场的相依性。实证表明,上证综指和深圳成指对数收益率存在高阶矩风险和风险的非对称性,即指数下跌时,条件方差风险和条件高阶矩风险会增大,且在极端情况下,两市上涨的概率要大于下跌的概率。Financial assets not only have variance risk, but also have time-varying skewness risk and kurtosis risk, which makes risk change study very limited if only based on the first or the second moment of the financial assets. GJRSK-M model is an effec- tive tool for higher moments risk description of the financial assets and can fit for the distribution of individual financial assets, however, M-Copula function can connect marginal distribution of portfolio financial assets, thus, this paper establishes M-Copula- GJRSK-M model to study the interdependence between Shanghai and Shenzhen stock market. The empirical results show that there are higher moment risk and risk asymmetry of the logarithm earnings rate of Shanghai composite index and Shenzhen component index, i.e, conditional variance risk and conditional higher moment risk increase when the index falls, furthermore, the probabili- ty for the index rise of the two stock markets is bigger than that of the index fall under the extreme condition.

关 键 词：M-Copula函数 GJRSK-M模型 高阶矩风险 

分 类 号：F224.0[经济管理—国民经济] F830.91