Should observational studies be designed to allow lack of balance in covariate distributions across treatment groups? REPLY

被引：60
作者：
Rubin, Donald B. [1 ]
机构：
[1] Harvard Univ, Dept Stat, Cambridge, MA 02138 USA
来源：
STATISTICS IN MEDICINE | 2009年 / 28卷 / 09期
关键词：
RANDOMIZED EXPERIMENTS; NONPARAMETRIC ANALYSIS; MISSING COVARIATE; OUTCOME DATA; INFERENCE;
D O I：
10.1002/sim.3565
中图分类号：
Q [生物科学];
学科分类号：
07 ; 0710 ; 09 ;
摘要：
引用
收藏
页码：1420 / 1423
页数：4
相关论文
共 13 条
[1]   Addressing complications of intention-to-treat analysis in the combined presence of all-or-none treatment-noncompliance and subsequent missing outcomes [J].
Frangakis, CE ;
Rubin, DB .
BIOMETRIKA, 1999, 86 (02) :365-379
[2]  
Horowitz JL, 2000, J AM STAT ASSOC, V95, P77, DOI 10.2307/2669526
[3]  
LANGENSKOLD S, 2008, ANN EC STAT IN PRESS
[4]   Nonparametric analysis of randomized experiments with missing covariate and outcome data - Comment [J].
Raghunathan, TE .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2000, 95 (449) :85-87
[5]   THE CENTRAL ROLE OF THE PROPENSITY SCORE IN OBSERVATIONAL STUDIES FOR CAUSAL EFFECTS [J].
ROSENBAUM, PR ;
RUBIN, DB .
BIOMETRIKA, 1983, 70 (01) :41-55
[6]  
ROSENBAUM PR, 1983, J ROY STAT SOC B MET, V45, P212
[7]   Direct and indirect causal effects via potential outcomes [J].
Rubin, DB .
SCANDINAVIAN JOURNAL OF STATISTICS, 2004, 31 (02) :161-170
[8]  
Rubin DB, 2004, SCAND J STAT, V31, P196, DOI 10.1111/j.1467-9469.2004.03-200C.x
[9]   INFERENCE AND MISSING DATA [J].
RUBIN, DB .
BIOMETRIKA, 1976, 63 (03) :581-590
[10]   BAYESIAN-INFERENCE FOR CAUSAL EFFECTS - ROLE OF RANDOMIZATION [J].
RUBIN, DB .
ANNALS OF STATISTICS, 1978, 6 (01) :34-58
12