缺失数据下变系数分位数回归模型的广义拟似然比检验  

Generalized Quasi-Likelihood Ratio Test of Varying Coefficient Quantile Regression Model with Missing Data

作　　者：王紧杰 罗双华[1] WANG Jinjie;LUO Shuanghua(School of Science,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学理学院,陕西西安710048

出　　处：《许昌学院学报》2022年第5期7-11,共5页Journal of Xuchang University

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：考虑一类缺失数据下变系数分位数回归模型的估计与推断问题.首先,运用Jackknife方法对变系数分位数回归模型中的系数函数进行了局部线性拟合.其次,构造了缺失数据下的广义拟似然比检验统计量,进而检验变系数分位数回归模型的系数.最后,在一定条件下证明了所构造统计量的大样本性质.Considering the estimation and inference of a quantile regression model with variable coefficients for a class of missing data,firstly,in the case of random missing covariates,the functional coefficients in a varying coefficient quantile regression model are estimated by applying local linear fitting technique with jackknife method.Secondly,the generalized quasi-likelihood ratio test statistic under missing data is constructed,and then the coefficient of the variable coefficient quantile regression model is tested.Finally,the large sample properties of the constructed statistics are proved under certain conditions.

关 键 词：缺失数据 变系数模型 分位数回归 广义拟似然比检验 

分 类 号：O212[理学—概率论与数理统计]