Minimizing Bias in Selection on Observables Estimators When Unconfoundness Fails
Daniel L. Millimet
Southern Methodist University (SMU) - Department of Economics; Institute for the Study of Labor (IZA)
Georgia State University - Department of Economics; National Bureau of Economic Research (NBER); Institute for the Study of Labor (IZA)
April 16, 2008
CAEPR Working Paper No. 2008-008
We characterize the bias of propensity score based estimators of common average treatment effect parameters in the case of selection on unobservables. We then propose a new minimum biased estimator of the average treatment effect. We assess the finite sample performance of our estimator using simulated data, as well as a timely application examining the causal effect of the School Breakfast Program on childhood obesity. We find our new estimator to be quite advantageous in many situations, even when selection is only on observables.
Number of Pages in PDF File: 38
Keywords: Treatment Effects, Propensity Score, Bias, Unconfoundedness, Selection on Unobservables
JEL Classification: C21, C52
Date posted: April 18, 2008 ; Last revised: May 12, 2008
© 2016 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollobot1 in 0.485 seconds