应用变系数分位点回归模型分析经济因素对全球股市风险的影响  

Using Varying Coefficient Quantile Regression Model to Analyze the Economic Factors' Impact on Stock Market Risk

作　　者：叶五一[1] 李国艳 缪柏其[1] YE Wu-yi;LI Guo-yan;MIAO Bai-qi(Department of Statistics and Finance,School of Management,University of Science and Technology of China,Anhui Hefei 230026,China)

机构地区：[1]中国科学技术大学管理学院统计与金融系,安徽合肥230026

出　　处：《数理统计与管理》2019年第1期132-144,共13页Journal of Applied Statistics and Management

基　　金：国家自然科学基金青年-面上连续项目(71371007);国家自然科学基金面上项目(71172214)

摘　　要：全球股市与经济因素之间关系一直是金融领域的热点问题,当前已有研究大都基于线性回归模型分析经济因素对股市收益率均值的影响。本文则基于变系数分位点回归模型研究了全球主要股票市场指数的市场风险与影响因素之间随时间变化的相依关系,对英国、法国、德国、加拿大、巴西、日本以及中国等主要国家股市1997年10月到2014年12月的数据进行了实证研究。实证研究结果表明,S&P500指数、商品市场(石油价格,黄金价格)等经济因素对全球主要股市的风险(下分位点)产生较为显著的影响,并且上述影响随着近期金融危机的发生而有所变化。相比之下,美国经济政策的不确定性、美国股市不确定性变化等对所分析国家股票市场风险的影响不显著。The analysis of the dependence structure between the stock markets of the major country of the world and influential global factors has always been a hot topic in international finance area. The literatures before focused on the impact of economic factors on the mean of stock returns by using the linear regression model. This paper examines the dependence structure between the stock markets of the major country of the world and influential global factors by using the quantile regression with varying coefficients approach. Our study base on the stock returns of Britain, France, Germany, Canada, Brazil,Japan and China for the period from October 1997 to December 2014. The results show that the stock markets risk(lower quantile) exhibit dependence with the global stock(S&P500 index) as well as the commodity markets(oil, gold). This dependence structure is affected by the onset of the recent global financial crisis. By contrast, the impact of the changes in the U.S. stock market uncertainty(CBOE Volatility Index)and the U.S. economic policyuncertainty is almost not significant.

关 键 词：全球影响因子 金融危机 变系数分位点回归模型 市场风险 

分 类 号：O212[理学—概率论与数理统计]