基于动态收缩法的大维协方差阵的估计及其应用
发布时间:2018-01-12 01:10
本文关键词:基于动态收缩法的大维协方差阵的估计及其应用 出处:《统计与决策》2017年10期 论文类型:期刊论文
【摘要】:文章将单因子协方差阵和样本协方差阵相结合,通过对它们进行最优加权平均,提出了新的协方差阵估计方法——动态加权收缩估计量(DWS)。该估计量一方面通过选择最优的权重来平衡协方差阵估计的偏差和误差;另一方面估计的是大维数据的动态协方差阵,在估计过程中考虑了前期信息的影响。通过模拟和实证研究发现:较传统的协方差阵估计方法而言,DWS估计量明显提高了大维协方差阵的估计效率;并且将其应用在投资组合时,投资者获得了更高的收益和经济福利。
[Abstract]:In this paper, the univariate covariance matrix and the sample covariance matrix are combined to carry out the optimal weighted average. A new covariance matrix estimation method, dynamic weighted contraction estimator, is proposed. On the one hand, the deviation and error of covariance matrix estimation are balanced by selecting the optimal weight. On the other hand, the dynamic covariance matrix of large dimensional data is estimated, and the influence of pre-information is taken into account in the estimation process. Through simulation and empirical research, it is found that: compared with the traditional covariance matrix estimation method. The DWS estimator obviously improves the estimation efficiency of the large dimensional covariance matrix. And when applied to the portfolio, investors get higher returns and higher economic benefits.
【作者单位】: 贵州财经大学数学与统计学院;德雷赛尔大学LeBoro商学院;
【基金】:国家社会科学基金青年项目(16CTJ013) 全国统计科学研究项目(2015LY19) 贵州省教育厅普通本科高校自然科学研究项目(黔教合KY字[2015]423)
【分类号】:F224;F830.9
【正文快照】: 0引言近年来,围绕如何估计大维协方差阵的估计问题,已经引起了学者们的广泛关注。目前的研究主要分为三类,第一类是稀疏协方差阵估计方法(Bickel和Levina(2008)[1],Rothman(2012)[2],Lam和Fan(2009)[3],Cai和Zhou(2012)[4],Cai和Liu(2011)[5]等),该方法假定有些资产之间是不相,
本文编号:1412018
本文链接:https://www.wllwen.com/jingjifazhanlunwen/1412018.html