On regression adjustments to experimental data

被引:204
作者
Freedman, David A. [1 ]
机构
[1] Univ Calif Berkeley, Dept Stat, Berkeley, CA 94720 USA
关键词
models; randomization; multiple regression; balance; intention-to-treat;
D O I
10.1016/j.aam.2006.12.003
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
Regression adjustments are often made to experimental data. Since randomization does not justify the models, almost anything can happen. Here, we evaluate results using Neyman's non-parametric model, where each subject has two potential responses, one if treated and the other if untreated. Only one of the two responses is observed. Regression estimates are generally biased, but the bias is small with large samples. Adjustment may improve precision, or make precision worse; standard errors computed according to usual procedures may overstate the precision, or understate, by quite large factors. Asymptotic expansions make these ideas more precise. (c) 2007 Published by Elsevier Inc.
引用
收藏
页码:180 / 193
页数:14
相关论文
共 26 条
[1]   STRONG CONSISTENCY OF LEAST-SQUARES ESTIMATES IN DYNAMIC-MODELS [J].
ANDERSON, TW ;
TAYLOR, JB .
ANNALS OF STATISTICS, 1979, 7 (03) :484-489
[2]  
[Anonymous], EXPT QUASI EXPT DESI
[3]  
[Anonymous], JASA
[4]  
[Anonymous], 2006, FUNDAMENTALS CLIN TR
[5]   Comparing experimental and matching methods using a large-scale voter mobilization experiment [J].
Arceneaux, K ;
Gerber, AS ;
Green, DP .
POLITICAL ANALYSIS, 2006, 14 (01) :37-62
[6]  
BRADY HE, 2004, RETHINKING SOCIAL IN
[7]   Women as policy makers: Evidence from a randomized policy experiment in India [J].
Chattopadhyay, R ;
Duflo, E .
ECONOMETRICA, 2004, 72 (05) :1409-1443
[8]  
DABROWSKA D, 1990, STAT SCI, V5, P463
[9]   Mediterranean diet, traditional risk factors, and the rate of cardiovascular complications after myocardial infarction - Final report of the Lyon Diet Heart Study [J].
de Lorgeril, M ;
Salen, P ;
Martin, JL ;
Monjaud, I ;
Delaye, J ;
Mamelle, N .
CIRCULATION, 1999, 99 (06) :779-785
[10]   CONSISTENCY OF LEAST SQUARES AND GAUSS-MARKOV ESTIMATORS IN REGRESSION MODELS [J].
DRYGAS, H .
ZEITSCHRIFT FUR WAHRSCHEINLICHKEITSTHEORIE UND VERWANDTE GEBIETE, 1971, 17 (04) :309-&