基于混合Copula函数的C-Vine贝叶斯推断

被引:1
作者
郑爽
梁冯珍
机构
[1] 天津大学理学院
关键词
C-Vine模型; 贝叶斯推断; 混合Copula函数; MCMC; 干球温度;
D O I
10.13546/j.cnki.tjyjc.2017.19.005
中图分类号
O212.8 [贝叶斯统计];
学科分类号
摘要
文章主要采用C-Vine模型,对模型进行贝叶斯推断。C-Vine模型利用二元Copula函数作为组块构造多维的相关结构,通过采用不同的二元Copula函数族来精确地捕捉变量间的相关性。采用Czado等提出的选择准则决定C-Vine模型的具体分解形式。利用AIC信息准则选择C-Vine模型中每条边合适的Copula函数族。利用马尔科夫链蒙特卡罗(MCMC)算法估计C-Vine模型的参数。最后,通过实例来研究序列间的相关性和相互影响。
引用
收藏
页码:24 / 28
页数:5
相关论文
共 7 条
  • [1] Copula modelling of dependence in multivariate time series
    Smith, Michael Stanley
    [J]. INTERNATIONAL JOURNAL OF FORECASTING, 2015, 31 (03) : 815 - 833
  • [2] Maximum likelihood estimation of mixed C-vines with application to exchange rates
    Czado, Claudia
    Schepsmeier, Ulf
    Min, Aleksey
    [J]. STATISTICAL MODELLING, 2012, 12 (03) : 229 - 255
  • [3] Modeling Longitudinal Data Using a Pair-Copula Decomposition of Serial Dependence
    Smith, Michael
    Min, Aleksey
    Almeida, Carlos
    Czado, Claudia
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2010, 105 (492) : 1467 - 1479
  • [4] Modeling covariance matrices via partial autocorrelations
    Daniels, M. J.
    Pourahmadi, M.
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2009, 100 (10) : 2352 - 2363
  • [5] Bayesian Copulae Distributions, with Application to Operational Risk Management[J] . Luciana Dalla Valle. Methodology and Computing in Applied Probability . 2009 (1)
  • [6] Pair-copula constructions of multiple dependence[J] . Kjersti Aas,Claudia Czado,Arnoldo Frigessi,Henrik Bakken. Insurance Mathematics and Economics . 2007 (2)
  • [7] Bayesian estimation of the Gaussian mixture GARCH model[J] . María Concepción Ausín,Pedro Galeano. Computational Statistics and Data Analysis . 2006 (5)