A Class of Unbiased Estimators of the Average Treatment Effect in Randomized Experiments

被引：45

作者：

Aronow, Peter M. ^{[1
]}

Middleton, Joel A. ^{[2
]}

机构：

[1] Yale Univ, New Haven, CT 06511 USA

[2] NYU, New York, NY 10003 USA

来源：

JOURNAL OF CAUSAL INFERENCE | 2013年 / 1卷 / 01期

关键词：

randomized experiments; unbiased estimation; average treatment effect; sampling theory;

D O I：

10.1515/jci-2012-0009

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

We derive a class of design-based estimators for the average treatment effect that are unbiased whenever the treatment assignment process is known. We generalize these estimators to include unbiased covariate adjustment using any model for outcomes that the analyst chooses. We then provide expressions and conservative estimators for the variance of the proposed estimators.

引用

页码：135 / 154

页数：20

共 48 条

[21]

Humphreys Marcartan, 2009, WORKING PAPER

[22] Variance identification and efficiency analysis in randomized experiments under the matched-pair design [J].