Principal Stratification - Uses and Limitations

被引：75

作者：

VanderWeele, Tyler J. ^{[1
]}

机构：

[1] Harvard Univ, Cambridge, MA 02138 USA

来源：

INTERNATIONAL JOURNAL OF BIOSTATISTICS | 2011年 / 7卷 / 01期

关键词：

causal inference; mediation; non-compliance; potential outcomes; principal stratification; surrogates; SENSITIVITY-ANALYSIS; CAUSAL INFERENCE; RANDOMIZED EXPERIMENTS; POST-RANDOMIZATION; BAYESIAN-INFERENCE; MEDIATION ANALYSIS; END-POINTS; VIRAL LOAD; OUTCOMES; TRIALS;

D O I：

10.2202/1557-4679.1329

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Pearl (2011) asked for the causal inference community to clarify the role of the principal stratification framework in the analysis of causal effects. Here, I argue that the notion of principal stratification has shed light on problems of non-compliance, censoring-by-death, and the analysis of post-infection outcomes; that it may be of use in considering problems of surrogacy but further development is needed; that it is of some use in assessing "direct effects"; but that it is not the appropriate tool for assessing "mediation." There is nothing within the principal stratification framework that corresponds to a measure of an "indirect" or "mediated" effect.

引用

页数：15

共 51 条

[31] Principal Stratification - a Goal or a Tool? [J].

Pearl, Judea .

INTERNATIONAL JOURNAL OF BIOSTATISTICS, 2011, 7 (01)

[32]

Pearl Judea, 2001, P 17 C UNCERTAINTY A, P411

[33]

Richardson Thomas S., 2011, Bayesian Statistics, V9, P10, DOI [DOI 10.1093/ACPROF:OSO/9780199694587.003.0019, 10.1093/acprof:oso/9780199694587.003.0019]

[34] A NEW APPROACH TO CAUSAL INFERENCE IN MORTALITY STUDIES WITH A SUSTAINED EXPOSURE PERIOD - APPLICATION TO CONTROL OF THE HEALTHY WORKER SURVIVOR EFFECT [J].