A MISSING INFORMATION PRINCIPLE AND M-ESTIMATORS IN REGRESSION-ANALYSIS WITH CENSORED AND TRUNCATED DATA

被引：43

作者：

LAI, TL ^{[1
]}

YING, ZL ^{[1
]}

机构：

[1] RUTGERS STATE UNIV,DEPT STAT,NEW BRUNSWICK,NJ 08903

来源：

ANNALS OF STATISTICS | 1994年 / 22卷 / 03期

关键词：

M-ESTIMATOR; CENSORING; TRUNCATION; SELF-CONSISTENCY; LINEAR REGRESSION; MARTINGALE; ASYMPTOTIC NORMALITY; INFLUENCE FUNCTION; ROBUSTNESS;

D O I：

10.1214/aos/1176325627

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：

A general missing information principle is proposed for constructing M-estimators of regression parameters in the presence df left truncation and right censoring on the observed responses. By making use of martingale central limit theorems and empirical process theory, the asymptotic normality of M-estimators is established under certain assumptions. Asymptotically efficient M-estimators are also developed by using data-dependent score functions. In addition, robustness properties of the estimators are discussed and formulas for their influence functions are derived for the robustness analysis.

引用

页码：1222 / 1255

页数：34