• 论文 • 上一篇    

M-Copula模型在金融时间序列分析中的研究与应用

王红军,王瑞花   

  1. 西安电子科技大学数学与统计学院,西安 710126
  • 出版日期:2020-06-25 发布日期:2020-08-25

王红军,王瑞花. M-Copula模型在金融时间序列分析中的研究与应用[J]. 系统科学与数学, 2020, 40(6): 1117-1132.

WANG Hongjun, WANG Ruihua. Research and Application of M-Copula Model in Financial Time Series Analysis[J]. Journal of Systems Science and Mathematical Sciences, 2020, 40(6): 1117-1132.

Research and Application of M-Copula Model in Financial Time Series Analysis

WANG Hongjun, WANG Ruihua   

  1. School of Mathematics and Statistics, Xidian University, Xi’an 710126
  • Online:2020-06-25 Published:2020-08-25

研究了M-Copula模型的建模方法及应用. 运用EM算法估计模型的参数, 得到相应的统计结果. 并利用M-Copula对上证综指和深证成指做了相关分析. 通过分析两样本数据的特征, 均建立了GARCH-$t$的边缘分布模型; 根据两个 对数收益率序列之间的相关特性, 选取M-Copula模型对其相关结构进行建模分析, 因M-Copula综合了不同Copula的特点, 所以分布形式更加灵活, 描述数据的厚尾和 相关性特征的能力更突出, 效果比单一的Copula更好.

This paper studies the modeling method and application of M-Copula model. The EM algorithm is used to estimate the parameters of M-Copula model, and the corresponding statistical results are obtained. We adopt M-Copula model to analyze the correlation between Shanghai Composite Index and Shenzhen Composite Index. By analyzing the characteristics of the two sample data, the GARCH-$t$ model is used to establish the marginal distribution model of its; and according to the correlation characteristics between two sequence of logarithmic return rates, the M-Copula model is adopted to model and analyze its related structure. Because M-Copula integrates the characteristics of different single Copulas, it has more flexible distribution forms and more prominent ability to describe the fat tails and correlation characteristics of data, and more importantly, the effect is better than the single Copula.

()
[1] 肖翔.  0-1膨胀几何分布回归模型及其应用[J]. 系统科学与数学, 2019, 39(9): 1486-1499.
[2] 李世凯,吴刘仓,詹金龙,易捷伊. 混合非线性联合均值与方差模型的统计推断[J]. 系统科学与数学, 2017, 37(2): 623-631.
[3] 叶飞,王翼飞. 混合高阶隐马氏模型的EM算法[J]. 系统科学与数学, 2013, 33(3): 334-350.
[4] 蒋卉;汤银才. 混合Weibull分布参数估计的ECM算法[J]. 系统科学与数学, 2010, 30(1): 79-088.
[5] 何书元;李睿;沈俊山. 右删失数据下的时间序列数据分析[J]. 系统科学与数学, 2007, 27(1): 20-26.
阅读次数
全文


摘要