股票收益率尾部相关性的Copula度量及模拟

股票收益率尾部相关性是研究金融市场关联性的重要内容.由于传统的τ、ρ等相关系数是对随机变量的全局度量,不适合用于收益率分布尾部这种局部特征的相关性度量.因此,在引入左尾(右尾)相关系数的基础上,讨论了它们的Copula度量及其相关性质.最后,通过计算机模拟分析了沪、深股指收益率尾部相关性的变化趋势,有效避免了Copula模型的设定困难,并得到了尾部相关性增强、相关不对称等结论.

Measuring and Simulating the Tail Dependence of Returns by Copula

The study on the tail dependence of returns is important for studying the dependence of the financial markets. Traditional correlation coefficients such as τ and ρ are not the best measures on the local dependence of returns,for they are usually used for the global measure of dependence.Then after the lower and upper-tail dependence coefficient introducted,the measure by Copula and correlative characters are studied.Finally,the tail dependence and its change current of the returns in shanghai and shenzhen securities exchange is analysed,and the conclusion about tail dependence is obtained.