基于加权指数平方损失的非负稳健估计与变量选择  

Non-negative Robust Estimation and Variable Selection Based on Weighted Exponential Squared Loss

作　　者：李孀孀 LI Shuang-shuang(School of Mathematical Sciences,Chongqing Normal University,Chongqing 401331,China)

机构地区：[1]重庆师范大学数学科学学院,重庆401331

出　　处：《兰州文理学院学报（自然科学版）》2024年第4期29-33,共5页Journal of Lanzhou University of Arts and Science(Natural Sciences)

基　　金：国家自然科学基金(12201091);重庆市自然科学基金面上项目(CSTB2022NSCQ-MSX0852);全国统计科学研究项目(2022LY019);重庆市教育委员会科学技术研究项目(KJQN202100526)。

摘　　要：针对估计参数具有非负要求的回归模型,基于自适应Lasso惩罚函数和加权指数平方损失,提出一种关于非负稳健估计与变量选择的方法.该方法保证了估计参数的非负要求,而且还能进行稳健的变量选择.数值模拟结果表明该方法与其他方法相比更有效.最后,将该方法运用到上证50指数的追踪,结果证明了所提方法的稳健性和有效性.Aiming at the regression model with non-negative requirements for estimating parameters,based on the adaptive Lasso penalty function and the weighted exponential squared loss,a method for non-negative robust estimation and variable selection is proposed.This method ensures the non-negative requirements of the estimated parameters,and also enables robust variable selection.Numerical simulation results show that the proposed method is more effective than other methods.Finally,the method is applied to the tracking of the SSE 50 index,and the results prove the robustness and effectiveness of the proposed method.

关 键 词：非负估计 加权指数平方损失 变量选择 稳健估计 

分 类 号：O212.1[理学—概率论与数理统计]