两阶段Logit模型的惩罚广义估计方程估计的渐近性质  

Asymptotic Properties of Estimation of Penalized Generalized Estimating Equations for Two Stage Logit Models

作　　者：林松 尹长明[1] LIN Song;YIN Changming(School of Mathematics and Information Science,Guangxi University,Nanning Guangxi 530004,China)

机构地区：[1]广西大学数学与信息科学学院,广西南宁530004

出　　处：《广西师范大学学报（自然科学版）》2019年第2期126-130,共5页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金(11061002);广西自然科学基金(2015GXNSFAA139006)

摘　　要：2012年Wang等在较弱条件下证明了经典Logit模型惩罚广义估计方程估计的渐近性质。两阶段Logit模型是经典Logit模型的推广,可以处理较复杂的属性数据,其联系函数(link)已不再是自然联系函数。本文在更弱条件下证明了两阶段Logit模型惩罚广义估计方程估计的渐近性质,推广了文献中的相应结果。Under the weaker conditions,the asymptotic properties of the estimation of the classical Logit model for the penalized generalized estimation equation are proved by Wang et al in 2012.The two-stage Logit model is a generalization of the classical Logit model,which can deal with more complex categorical data,and its link function(link)is no longer a natural relation function.In this paper,the asymptotic properties of the estimation of the penalty generalized estimation equation for two-stage Logit model under weaker conditions are proved,and the corresponding results in the literature are generalized.

关 键 词：两阶段Logit回归 惩罚广义估计方程 高维协变量 纵向数据 一般联系函数 

分 类 号：O212.1[理学—概率论与数理统计]