基于多分布GARCH族模型的沪深300指数VaR测度研究

发布时间：2018-01-23 19:42

本文关键词： GARCH族模型 VaR测度返回测试风险测度金融风险股票指数期货投资　出处：《东岳论丛》2016年12期 　论文类型：期刊论文

【摘要】：运用经济物理学方法验证沪深300指数市场存在的一些特征,进而用四种GARCH模型在不同分布下进行VaR风险测度建模,并用返回测试中的似然比和动态分位数回归加以检验,结果表明:收益分布服从有偏学生t分布的VaR测度模型可靠性显著高于正态分布和学生t分布;在样本内,GARCH、GJR、HYGARCH模型均能有效度量VaR风险,HYGARCH在空头VaR水平较高时精度更高;在样本外,GARCH、GJR、FIGARCH、HYGARCH模型的VaR测度能力相差不大,但HYGARCH模型在空头VaR水平下测度能力更高些。因此,在有偏学生t分布下,能捕捉更多金融资产特征的HYGARCH模型对沪深300指数的VaR测度更精确可靠,这意味着在风险管理时,应更多考虑具有尾部效应的模型进行度量。
[Abstract]:Using the economic physics method to verify some characteristics of Shanghai and Shenzhen 300 index market, and then use four kinds of GARCH models to model the VaR risk measurement under different distribution. The likelihood ratio and dynamic quantile regression in return test are used to test the results. The results show that the reliability of the VaR measure model of income distribution is significantly higher than that of normal distribution and student t distribution. The VaR risk can be effectively measured by the GJR GJR HYGARCH model in the sample. The accuracy of HYGARCH is higher when the short VaR level is higher than that of the HYGARCH model. There is little difference in the VaR measurement ability of the GARCHN GJRK FIGARCHH HYGARCH model outside the sample. However, the HYGARCH model is more capable of measuring at the level of short VaR. Therefore, in the case of biased student t distribution. The HYGARCH model, which can capture more characteristics of financial assets, is more accurate and reliable for the VaR measurement of the CSI 300 index, which means that in risk management. More consideration should be given to the measurement of models with tail effects.
【作者单位】：齐鲁工业大学工商学院;潍阴工学院管理工程学院;
【分类号】：F830.91
【正文快照】： (1)Mantegna,R.N.and H.E.Stanley:Scaling behaviour in the dynamics of an economic index,376(6535),pp.46-49,1995.(2)Kantelhardt,J.W.,S.A.Zschiegner,E.Koscielny-Bunde,S.Havlin,A.Bunde and H.E.Stanley:Multifractal detrendedfluctuation analysis of nonstationa

【相似文献】