基于横截面回归和Fama-MacBeth估计的鲁棒投资组合优化问题研究  

Robust portfolio selection based on cross-sectional regression and Fama-Macbeth estimator

作　　者：江波 朱喜华[1] JIANG Bo;ZHU Xihua(School of Information Management and Engineering,Shanghai University of Finance and Economics,Shanghai 200433,China;Research Institute for Interdisciplinary Sciences,Shanghai University of Finance and Economics,Shanghai 200433,China)

机构地区：[1]上海财经大学信息管理与工程学院,上海200433 [2]上海财经大学交叉科学研究院,上海200433

出　　处：《运筹学学报》2021年第3期133-146,共14页Operations Research Transactions

基　　金：国家自然科学基金(Nos.11771269,11831002);上海财经大学研究生创新基金(No.CXJJ-2019-391)。

摘　　要：考虑了不同于Goldfarb和Iyengar(2003)的因子模型,通过横截面回归分析以及Fama-MacBeth估计构造了关于资产的平均收益向量和协方差矩阵的不确定性集合(置信区域)。基于这些不确定性集合以及Markowitz"均值-方差模型"的鲁棒投资组合问题,提出了多个鲁棒投资组合问题,并对应的推导出其等价的半正定规划形式,使得问题可以在多项式时间内求解。This paper considers a factor model different from Goldfarb and Iyengar(2003)and the uncertainty set for the mean profit vector and covariance matrix of the assets in the robust problems are constructed by the cross-sectional regression and Fama-MacBeth estimator.Based on the robust portfolio selection problems under the Markowitz mean-variance model and these uncertainty sets,we prosed multiple robust portfolio selection problems and prove that these problems can be re-written as Semidefinite programmings which are computationally tractable.

关 键 词：鲁棒优化 均值-方差模型 横截面因子模型 半正定规划 

分 类 号：F224.3[经济管理—国民经济] O224[理学—运筹学与控制论]