论文部分内容阅读
结合相依结构函数Copula和极值理论EVT,构建了我国股票市场经流动性调整的La-Copula-EVT风险价值模型,并用沪深收益序列的分笔高频数据进行了实证分析,发现我国沪深股市收益序列的上尾和下尾都存在较高相关性,后验测试结果表明构建的模型能够对实际损失进行很好的拟合;然后在该模型的基础上进一步分析了我国沪深股市的风险价值和预期不足在不同置信区间的敏感度差异,确定了适合La-Copula-EVT模型的最优置信度区间。
The La-Copula-EVT VaR model of China’s stock market adjusted with liquidity is constructed by combining Copula with exponential structure function EVT. Empirical analysis is made on the data of high and low frequency of Shanghai and Shenzhen yield series. It is found that Shanghai-Shenzhen There is a high correlation between the upper tail and the lower tail of the stock return series. The posterior test results show that the constructed model can well fit the actual loss. Based on this model, the risk of the Shanghai and Shenzhen stock markets is further analyzed Value and expected deficit in different confidence intervals, the best confidence interval suitable for La-Copula-EVT model is determined.