响应数据缺失下一般线性分位数回归模型的估计  

Estimation of general linear quantile regression model with missing response data

作　　者：黄婉娟 罗双华[1] 张成毅 HUANG Wanjuan;LUO Shuanghua;ZHANG Chengyi(School of Science,Xi’an Polytechnic University,Xi’an 710048,China;School of Economics and Finance,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]西安工程大学理学院,陕西西安710048 [2]西安交通大学经济与金融学院,陕西西安710049

出　　处：《纺织高校基础科学学报》2022年第4期111-119,共9页Basic Sciences Journal of Textile Universities

基　　金：国家自然科学基金(11601409);陕西省自然科学基金(2020JM571,2021JM-002)。

摘　　要：在响应数据缺失条件下研究了一般线性分位数回归模型的估计问题。利用处理缺失数据的逆概率加权方法,在缺失概率已知、缺失概率未知时的非参数估计和参数估计3种情况下,给出了一般线性复合分位数回归模型的3种参数估计;在合适的条件下,证明了所给估计的渐近正态性。通过数值实验验证了所得估计的有效性。In order to deal with the problem of missing data in practical problems,this paper studies the estimation problem of general linear quantile regression model with missing response data.By using the inverse probability weighting method for missing data,three parameter estimators of the general linear composite quantile regression model are given in three cases:the missing probability is known,estimated nonparametric and parameter,respectively.The established parameter estimators are proved to be asymptotic normal under some appropriate regularity conditions.The performance of the estimators is assessed by numerical simulation.

关 键 词：缺失数据 缺失概率 一般线性模型 复合分位数回归 渐近正态性 

分 类 号：O212[理学—概率论与数理统计]