论文部分内容阅读
探索金融市场极端风险传导机理一直是政府管理当局、投资者关注的焦点。本文针对股市中存在的典型事实及股市损失分布复杂性特点,运用ARMA-GJR对股市指数条件损失进行建模分析,进而运用EVT对标准残差的极值尾部建模估计出股市极端风险ES,然后运用Granger-Causality检验技术,分别考察两个市场间极端风险ES的传导关系。实证结果表明:在整个样本期间,中国大陆沪深股市极端风险具有双向传导关系,香港市场向深市传导风险,而深市不能向香港传导风险,东京市场与香港市场、香港与台湾市场具有双向传导关系;而在熊市期间,中国大陆与周边市场极端风险ES传导关系变得更为复杂。
To explore the mechanism of extreme risk transmission in financial markets has always been the focus of government management and investors. In this paper, according to the typical facts in the stock market and the complexity of the distribution of the loss of the stock market, ARMA-GJR is used to model the stock market index conditional loss, and then EVT is used to model the extreme residuals of the standard residuals to estimate the extreme risk ES, Then using the Granger-Causality test technique, the conduction relationship between the extreme risk ES in the two markets was investigated respectively. The empirical results show that during the entire sample period, the extreme risks of the Shanghai and Shenzhen stock markets in Mainland China have a two-way conduction relationship. The Hong Kong market conducts risks to the Shenzhen Stock Exchange, while the Shenzhen Stock Exchange can not conduct risks to Hong Kong. The Tokyo and Hong Kong markets, Hong Kong and Taiwan markets have bidirectional Conduction relationship; and during the bear market, the mainland China and the peripheral market, extreme risk ES conduction relationship has become more complicated.