响应数据缺失下单指标回归模型的经验似然  

Empirical likelihood estimation of single index quantile regression model with missing response data

作　　者：刘璇 罗双华[1] 张成毅 LIU Xuan;LUO Shuang-hua;ZHANG Cheng-yi(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,西安710048 [2]西安交通大学经济与金融学院,西安710049

出　　处：《哈尔滨商业大学学报（自然科学版）》2023年第2期192-199,共8页Journal of Harbin University of Commerce：Natural Sciences Edition

基　　金：陕西省自然科学基金(2020JM571,2021JM-002)。

摘　　要：为研究响应数据缺失下单指标分位数回归模型的估计问题.采用经验似然估计方法,给出了响应数据缺失下的单指标分位数回归模型的经验对数似然比和单指标分位数回归模型的参数估计.在一定条件下证明了所得的经验对数似然比服从卡方分布和分位数经验似然估计服从渐近正态分布.通过数值模拟实验说明了所得估计的有效性.This paper studied on the estimation problem of the single-index quantile regression model under the missing response data.The empirical log-likelihood ratio and parameter estimation of the single-index quantile regression model with missing response data were given by using the empirical likelihood estimation method.It was proved that the empirical log-likelihood ratio obeys the Chi-square distribution and the quantile empirical likelihood estimator obeys the asymptotic normal distribution under certain conditions.The performance of the estimators was assessed by numerical simulation.

关 键 词：缺失数据 单指标模型 分位数回归 经验似然 渐近正态性 

分 类 号：O212[理学—概率论与数理统计]