Estimation of treatment effects in randomized trials with non-compliance and a dichotomous outcome

被引:17
作者
van der Laan, Mark J. [1 ]
Hubbard, Alan [1 ]
Jewell, Nicholas P. [1 ]
机构
[1] Univ Calif Berkeley, Div Biostat, Berkeley, CA 94720 USA
关键词
binary outcome; causal treatment effect; counterfactual; generalized quantile-quantile function; instrumental variable; non-compliance;
D O I
10.1111/j.1467-9868.2007.00598.x
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
We propose a class of estimators of the treatment effect on a dichotomous outcome among the treated subjects within covariate and treatment arm strata in randomized trials with non-compliance. Recent papers by Vansteelandt and Goetghebeur, and Robins and Rotnitzky have presented consistent and asymptotically linear estimators of a causal odds ratio, which rely, beyond correct specification of a model for the causal odds ratio, on a correctly specified model for a potentially high dimensional nuisance parameter. In this paper we propose consistent, asymptotically linear and locally efficient estimators of a causal relative risk and a new parameter-called a switch causal relative risk-which relies only on the correct specification of a model for the parameter of interest. Our estimators are always consistent and asymptotically linear at the null hypothesis of no-treatment effect, thereby providing valid testing procedures. We examine the finite sample properties of these instrumental-variable-based estimators and the associated testing procedures in simulations and a data analysis of decaffeinated coffee consumption and miscarriage.
引用
收藏
页码:463 / 482
页数:20
相关论文
共 22 条
[1]   Semiparametric instrumental variable estimation of treatment response models [J].
Abadie, A .
JOURNAL OF ECONOMETRICS, 2003, 113 (02) :231-263
[2]  
Angrist JD, 1996, J AM STAT ASSOC, V91, P444, DOI 10.2307/2291629
[3]  
[Anonymous], LATENT VARIABLE MODE
[4]  
[Anonymous], 1990, Stat Sci, DOI DOI 10.1214/SS/1177012031
[5]  
[Anonymous], J AM STAT ASSOC
[6]  
BALKE A, 1994, P 10 C UNC ART INT S, P46
[7]   Caffeinated beverages, decaffeinated coffee, and spontaneous abortion [J].
Fenster, L ;
Hubbard, AE ;
Swan, SH ;
Windham, GC ;
Waller, K ;
Hiatt, RA ;
Benowitz, N .
EPIDEMIOLOGY, 1997, 8 (05) :515-523
[8]  
Hirano K, 2000, Biostatistics, V1, P69, DOI 10.1093/biostatistics/1.1.69
[9]   Modeling treatment effects on binary outcomes with grouped-treatment variables and individual covariates [J].
Johnston, SC ;
Henneman, T ;
McCulloch, CE ;
van der Laan, M .
AMERICAN JOURNAL OF EPIDEMIOLOGY, 2002, 156 (08) :753-760
[10]   PREDICTING LIKELIHOOD OF GASTROENTERITIS FROM SEA BATHING - RESULTS FROM RANDOMIZED EXPOSURE [J].
KAY, D ;
FLEISHER, JM ;
SALMON, RL ;
JONES, F ;
WYER, MD ;
GODFREE, AF ;
ZELENAUCHJACQUOTTE, Z ;
SHORE, R .
LANCET, 1994, 344 (8927) :905-909