摘要
研究了度量相关性的两个工具:秩相关系数和尾部相关系数.在Archimedean Copula族中选择最优的Clayton Copula来度量上证综指和深圳成指尾部相关性,得出两者具有较强的下尾相关性,且量化后的相关性能够较好预测股票市场的变化.
Rank dependence coefficient and tail dependence coefficient are studied in this paper. Clayton Copula is Selected to the best Copula in Archimedean Copula to measure the correlation between SHI and SZI, the research indicate that the correlation of the .two indexes can be characterized through lower tail dependence, and the tail quantified dependence could forecast the change in stock market in the future.
出处
《山西师范大学学报(自然科学版)》
2007年第3期28-32,共5页
Journal of Shanxi Normal University(Natural Science Edition)
关键词
COPULA函数
秩相关系数
尾部相关系数
copula function
rank dependence coefficient
tail dependence coefficient