摘要
本文运用机制转换混合Copula函数研究了沪深300股指期货与沪深300指数之间的尾部传染,用AR(1)-GJR(1,1)-t模型描述沪深股指期货和现货收益率的边缘分布,以机制转换混合Copula函数对股指期货与现货收益率间的尾部相依结构进行建模,刻画了沪深300股指期货与现货2010年4月16日至2013年2月1日期间的尾部相依结构,并分析了两市之间的尾部传染性。实证结果表明:机制转换混合Copula模型比无机制转换的混合Copula模型更能够准确地描述两个市场之间的尾部相依结构;两个市场上尾的相依关系要强于下尾的相依关系;在整个研究期间内两市发生了明显的尾部风险传染。
This paper constructs a regime-switching mixed Copula model to research the tail contagion of CSI300 index futures and CSI300 index. Apply AR （ 1 ） -GJR （ 1,1 ） -t model to describe the marginal distribution of CSI 300 index futures and spots return rates, and regime-switching mixed Copula model to describe the dependence structure of stock index futures and spots return rates. Describe the dependence structure of CSI index futures and spots from April 16, 2010 to February 1, 2013 and analyse the tail contagion of the two markets. The empirical results show that regime- switching mixed Copula model can more accurately describe tail dependence structure of two markets than mixed Copula model. Moreover, the dependence relation of upper tail of two markets is stronger than the dependence relation of lower tail and the two markets occurred obviously tail risk contagion in the research period.
出处
《预测》
CSSCI
北大核心
2014年第5期30-35,47,共7页
Forecasting
基金
国家自然科学基金资助项目(71171025)
国家社会科学基金资助项目(12BGL024)
四川省科技计划资助项目(2012ZR0045)
成都理工大学优秀科研创新团队资助项目(KYTD201303)
