Estimating Causal Effects With Matching Methods in the Presence and Absence of Bias Cancellation
Open Access
- 1 May 2004
- journal article
- Published by SAGE Publications in Sociological Methods & Research
- Vol. 32 (4) , 501-528
Abstract
This article explores the implications of bias cancellation on the estimate of average treatment effects using ordinary least squares (OLS) and Rubin-style matching methods. Bias cancellation (offsetting biases at high and low propensities for treatment in estimates of treatment effects that are uncorrected for nonrandom selection) has been observed when job training is the treatment variable and earnings is the outcome variable. Contrary to published assertions in the literature, bias cancellation is not explainable in terms of the standard selection model, which assumes a symmetric distribution for the errors in the structural and assignment equations. A substantive rationale for bias cancellation is offered, which conceptualizes bias cancellation as the result of a mixture process based on two distinct individual-level decision-making models. While the general properties are unknown, the existence of bias cancellation appears to reduce the average bias in both OLS and matching methods relative to the symmetric distribution case.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Earnings and Employment Effects of Continuous Off-the-Job Training in East Germany after UnificationJournal of Business & Economic Statistics, 1999
- The Economics and Econometrics of Active Labor Market Programs1999
- Characterizing Selection Bias Using Experimental DataEconometrica, 1998
- Matching As An Econometric Evaluation EstimatorReview of Economic Studies, 1998
- Matching As An Econometric Evaluation Estimator: Evidence from Evaluating a Job Training ProgrammeReview of Economic Studies, 1997
- Instrumental Variables: A Study of Implicit Behavioral Assumptions Used in Making Program EvaluationsThe Journal of Human Resources, 1997
- Identification of Causal Effects Using Instrumental VariablesJournal of the American Statistical Association, 1996
- Reducing Bias in Observational Studies Using Subclassification on the Propensity ScoreJournal of the American Statistical Association, 1984
- Prospect Theory: An Analysis of Decision under RiskEconometrica, 1979
- Sample Selection Bias as a Specification ErrorEconometrica, 1979