基于copula方法的创业板与上证市场相关性研究

发布时间：2018-03-22 13:55

本文选题：创业板　切入点：时变copula　出处：《中国科学技术大学》2014年硕士论文　论文类型：学位论文

【摘要】：本文主要研究了中国创业板市场与沪市日收益率间的相依关系.我们选取创业板价格指数和上证综合指数的日收盘价数据,将时变t-copula模型,ARMA-GARCH模型和有偏误差分布结合起来构成了一个复合模型,并利用马尔科夫链蒙特卡洛方法对所有的参数给出了贝叶斯估计.估计所得的两市场间Kendall秩相关系数的图形显示了创业板和主板市场之间确实存在着一种时变的正相依关系.进一步,我们对两市场在不同行业板块中日收益率的相依关系进行了类似地建模.结果显示两市场在工业板块中的相依结构与市场整体十分相近,而在信息技术板块中则存在着更强更稳定的正相依关系.同时,我们发现了市场整体和工业板块内Kendall秩相关系数的上下波动存在一定模式,并尝试对其进行解释.
[Abstract]:This paper mainly studies the relationship between the daily yield of China gem market and Shanghai Stock Exchange. We select the daily closing price data of the gem price index and the Shanghai Composite Index. The ARMA-GARCH model of time-varying t-copula is combined with the biased error distribution to form a composite model. The Bayesian estimation of all the parameters is given by using Markov chain Monte Carlo method. The graph of the Kendall rank correlation coefficient between the two markets shows that there is a time-varying relationship between the gem and the main board market. Positive dependency. Further, We model the dependence of the daily yield in different industry sectors in a similar way. The results show that the dependence structure of the two markets in the industrial sector is very similar to that of the market as a whole. In the information technology sector, there is a stronger and more stable positive dependency. At the same time, we find that there is a certain model for the fluctuation of Kendall rank correlation coefficient in the whole market and the industrial plate, and try to explain it.
【学位授予单位】：中国科学技术大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：F832.51;O212.8

【参考文献】