基于贝叶斯多变量厚尾随机波动模型的期货与现货联动效应研究.pdfVIP

中国科技论文在线 基于贝叶斯多变量厚尾随机波动模型的期 货与现货联动效应研究# 朱慧明，王延彦，马超群，游万海，邓慧敏* 5 （湖南大学工商管理学院，长沙410082 ） 摘要：针对多变量随机波动模型难以刻画金融时间序列尖峰厚尾特征的问题，构建了贝叶斯 多变量厚尾随机波动模型。通过模型的贝叶斯分析，选择参数先验分布，设计基于Gibbs 抽 样的MCMC 算法，据此估计模型参数，解决多变量随机波动模型参数较多难以估计的问题； 10 并利用沪深300 股指期货与现货交易数据进行实证分析。研究结果表明：贝叶斯多变量厚尾 随机波动模型能更准确地刻画金融市场的波动特征以及金融市场间的波动溢出效应。 关键词：股指期货；波动溢出；随机波动；贝叶斯分析；Gibbs 算法 中图分类号：F830.91 15 Research of the Linkage Effect between Futures and Spot: Evidence from Bayesian Multivariate Heavy-tailed Stochastic Volatility Model ZHU Huiming, WANG Yanyan, MA Chaoqun, YOU Wanhai, DENG Huimin (College of Business Administration, Hunan University, Changsha 410082) 20 Abstract: To solve the problem that multivariate stochastic volatility model cannot describe heavy-tailed characteristics of financial time series, this paper proposes a Bayesian heavy-tailed stochastic volatility model. Based on the analysis of model statistic structure and the selection of parameters prior, the paper constructs a Markov Chain Monte Carlo algorithm procedure with Gibbs sampler to estimate parameters, avoiding the difficulty of parameter estimation. The suggested 25 approach is applied to analyze the linkage effect between CSI 300 futures market and spot market. The results show that the proposed model describes not only volatility character of financial market more accurately, but also volatility spillover effect of the two financial markets. Key words: Stock Index Futures; Volatility Spillover; Stochastic Volatility; Bayesian analysis ；Gibbs Algorithm 30