Maximum weighted likelihood for discrete choice models with a dependently censored covariate

被引：1
|
作者：
Lv, Xiaofeng [1 ]
Zhang, Gupeng [2 ]
Li, Qinghai [3 ]
Li, Rui [4 ]
机构：
[1] Southwestern Univ Finance & Econ, Sch Int Business, Chengdu, Sichuan, Peoples R China
[2] Univ Chinese Acad Sci, Sch Publ Policy & Management, Beijing 100049, Peoples R China
[3] Nanjing Univ Finance & Econ, Sch Econ, Nanjing, Jiangsu, Peoples R China
[4] Beijing Normal Univ, Sch Business, 19 XinJieKouWai St, Beijing 100875, Peoples R China
来源：
JOURNAL OF THE KOREAN STATISTICAL SOCIETY | 2017年 / 46卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Discrete choice models; Maximum weighted likelihood; Censored covariate; CONFIDENCE-INTERVALS; QUANTILE REGRESSION; AUXILIARY INFORMATION; UNEMPLOYMENT; ESTIMATOR;
D O I：
10.1016/j.jkss.2016.05.007
中图分类号：
O21 [概率论与数理统计]; C8 [统计学];
学科分类号：
020208 ; 070103 ; 0714 ;
摘要：
This study considers discrete choice models with a censored covariate under dependent censoring where the censoring mechanism depends on the outcomes of choice models. We estimate the parameter vector using maximum weighted likelihood (MWL). The weights are obtained through the Aalen's estimator. Our estimator for the parameter vector in choice models is consistent and asymptotically normal. Simulations show that MWL performs well. Finally, the proposed MWL method is applied to a real data set. (C) 2016 The Korean Statistical Society. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码：15 / 27
页数：13
相关论文
共 50 条
12345