基于藤Copula的中美股市风险溢出研究  

The Study on the Risk Spillover Effect of International Stock Market Based on High-Dimensional Vine Copula

作　　者：王凤雪 冯继国 涂欣然 

机构地区：[1]北方工业大学理学院,北京

出　　处：《金融》2020年第5期470-477,共8页Finance

摘　　要：文章首先通过GARCH(1,1)-t模型对各主要股市指数收益率数据的边缘分布进行拟合,并提取降噪处理后的残差序列;接着采用极值理论中的GPD分布残差序列的尾部进行拟合;然后基于高维的C-Vine Copula模型确定各个收益率间的相依关系及联合分布;然后结合C-Vine Copula模型与条件风险(CoVaR)计算中美几个重要股市间的风险溢出效应。结果表明:美国股票市场尤其是纳斯达克市场对中国股市有强溢出效应,且主要是通过香港市场对内地市场进行风险传染。In this paper, we firstly used the GARCH(1,1)-t model to fit the marginal distribution of the yield data of each major stock market index, and extract the residual sequence after noise reduction;then use the GPD distribution in extreme theory to fit the tail of the residual sequence, then based on the high-dimensional C-Vine Copula model to determine the dependency relationship and joint distribution of each rate of return;and combine with the C-Vine Copula model and conditional risk (CoVaR) to calculate the risk spillover effect between several important stock markets in China and the United States. The results show that the US stock market, especially the Nasdaq market, has a strong spillover effect on the Chinese stock market, and it is mainly through the Hong Kong mar-ket’s risk contagion of the mainland market.

关 键 词：GPD分布 Vine Copula模型 条件风险值(CoVaR) 

分 类 号：F83[经济管理—金融学]