删失指标随机缺失下条件分位数的加权双核局部线性估计  

Weighted Double-Kernel Local Linear Estimators of Conditional Quantiles with Censoring Indicators Missing at Random

作　　者：王江峰[1] 李国定 郦颖蕾 熊怡 WANG Jiangfeng;LI Guoding;LI Yinglei;XIONG Yi(School of Statistics and Mathematics,Zhejiang Gongshang University,Hangzhou 310018)

机构地区：[1]浙江工商大学统计与数学学院,杭州310018

出　　处：《系统科学与数学》2021年第9期2621-2642,共22页Journal of Systems Science and Mathematical Sciences

基　　金：国家社会科学基金(20BTJ049)资助课题。

摘　　要：文章在删失指标随机缺失下,当协变量为多维时,分别构造了条件分布函数的加权双核局部线性校准估计、插值估计以及逆概率估计;进一步,利用这些估计导出了条件分位数的相应估计,并建立了这些估计的渐近正态性结果;最后,通过模拟分析了这些估计在有限样本数据下的渐近性质.In this paper,we construct a weighted double-kernel local linear calibration estimator,an imputation estimator and an inverse probability estimator of conditional distribution function when censoring indicators are missing at random and covariates are multidimensional.Furthermore,the corresponding estimators of conditional quantiles are derived by using these estimators,and the asymptotic normality results of these estimators are established.Finally,the simulation studies are conducted to illustrate the finite sample performance of the estimators.

关 键 词：删失指标 随机缺失 条件分位数 局部线性估计 渐近正态性 

分 类 号：O212.1[理学—概率论与数理统计]