基于复合分位数回归的最小二乘模型平均  

Least Squares Model Average Based on Composite Quantile Regression

作　　者：吴修平 WU Xiu-ping(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）》2023年第6期25-29,共5页Journal of Lanzhou University of Arts and Science(Natural Sciences)

摘　　要：在所有预测候选模型都可能是错误指定的情况下,提出了一种稳健的复合分位数回归模型平均方法.在一定正则条件下,证明了该方法不受回归变量排序问题的影响,且该方法具有渐近最优性.仿真结果验证了该方法的优良性.This paper proposes a frequency model averaging method when considering that all prediction candidate models may be incorrectly specified.Under certain regularization conditions,it has been proven that this method is not affected by the ranking problem of regression variables and has asymptotic optimality.The simulation results verify the superiority of the method proposed in this paper.

关 键 词：复合分位数 模型平均 最小二乘 渐近最优性 

分 类 号：O213.9[理学—概率论与数理统计]