ESTIMATION OF THE MEAN WHEN DATA CONTAIN NON-IGNORABLE MISSING VALUES FROM A RANDOM EFFECTS MODEL

被引：4

作者：

SHIH, WCJ

QUAN, H

CHANG, MN

机构：

[1] MERCK SHARP & DOHME LTD,BIOSTAT & RES DATA SYST,RAHWAY,NJ 07065

[2] UNIV FLORIDA,DEPT STAT,GAINESVILLE,FL 32611

来源：

STATISTICS & PROBABILITY LETTERS | 1994年 / 19卷 / 03期

关键词：

MISSING VALUES; RANDOM EFFECTS MODEL; NON-IGNORABLE MISSING DATA PROCESS; MISSING AT RANDOM; DISTINCT PARAMETERS; EM ALGORITHM; ECM ALGORITHM;

D O I：

10.1016/0167-7152(94)90112-0

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 paper is concerned with the inference of incomplete data when the missing data process is non-ignorable in the sense of Rubin (Biometrica 38 (1982) 963-974). With the random effects model and the proposed missing data process, the conditions missing at random (MAR) and distinct parameters (DP) are discussed. The impact of the missing data is illustrated by the asymptotic bias of the sample mean based on only the observed data and ignoring the missing data process. Maximum likelihood and moment estimators of the marginal mean are obtained.

引用

页码：249 / 257

页数：9

共 13 条

[1]

ANDERSON S, 1986, AM J MED, V80, P501

[2]

CHESHER A, 1991, BIOMETRIKA, V78, P451

[3] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].

DEMPSTER, AP ;

LAIRD, NM ;

RUBIN, DB .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38

[4]

DIGGLE PJ, 1993, INFORMATIVE RANDOM D

[5]

DIGGLE PJ, 1992, IN PRESS BIOMETRICS

[6]

Fuller Wayne A., 1987, MEASUREMENT ERROR MO, DOI DOI 10.1002/9780470316665

[7] EMPIRICAL BAYES ESTIMATION OF RATES IN LONGITUDINAL-STUDIES [J].

HUI, SL ;

BERGER, JO .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1983, 78 (384) :753-760

[8] RANDOM-EFFECTS MODELS FOR LONGITUDINAL DATA [J].

LAIRD, NM ;

WARE, JH .

BIOMETRICS, 1982, 38 (04) :963-974

[9]

MENG XL, 1993, IN PRESS BIOMETRIKA

[10]

RUBIN DB, 1976, BIOMETRIKA, V63, P581, DOI 10.2307/2335739

← 1 2 →