Principal Stratification - a Goal or a Tool?

被引:76
作者
Pearl, Judea [1 ]
机构
[1] Univ Calif Los Angeles, Los Angeles, CA 90024 USA
基金
美国国家科学基金会;
关键词
causal inference; principal stratification; surrogate endpoints; direct effect; mediation; CAUSAL INFERENCE; IDENTIFICATION; EXCHANGEABILITY; IDENTIFIABILITY; DESIGN; MODEL;
D O I
10.2202/1557-4679.1322
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Principal stratification has recently become a popular tool to address certain causal inference questions, particularly in dealing with post-randomization factors in randomized trials. Here, we analyze the conceptual basis for this framework and invite response to clarify the value of principal stratification in estimating causal effects of interest.
引用
收藏
页数:14
相关论文
共 47 条
[1]   Generalized Causal Mediation Analysis [J].
Albert, Jeffrey M. ;
Nelson, Suchitra .
BIOMETRICS, 2011, 67 (03) :1028-1038
[2]  
Angrist JD, 1996, J AM STAT ASSOC, V91, P444, DOI 10.2307/2291629
[3]  
[Anonymous], IDENTIFICATION INFER
[4]  
[Anonymous], R372 U CAL DEP COMP
[5]  
[Anonymous], STAT CAUSAL IN PRESS
[6]  
[Anonymous], 2009, CAUSALITY MODELS REA
[7]  
Avin C, 2005, 19TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-05), P357
[8]   THE PAIRED AVAILABILITY DESIGN - A PROPOSAL FOR EVALUATING EPIDURAL ANALGESIA DURING LABOR [J].
BAKER, SG ;
LINDEMAN, KS .
STATISTICS IN MEDICINE, 1994, 13 (21) :2269-2278
[9]   Bounds on treatment effects from studies with imperfect compliance [J].
Balke, A ;
Pearl, J .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1997, 92 (439) :1171-1176
[10]  
BALKE A, 1994, PROCEEDINGS OF THE TWELFTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2, P230