Published March 2014
| Version Published
Journal Article
Open
Identifying Treatment Effects Under Data Combination
Creators
-
1.
University of Washington
-
2.
California Institute of Technology
Abstract
We consider the identification of counterfactual distributions and treatment effects when the outcome variables and conditioning covariates are observed in separate data sets. Under the standard selection on observables assumption, the counterfactual distributions and treatment effect parameters are no longer point identified. However, applying the classical monotone rearrangement inequality, we derive sharp bounds on the counterfactual distributions and policy parameters of interest.
Additional Information
© 2014 The Econometric Society. Manuscript received February, 2012; final revision received October, 2013. Article first published online: 1 Apr. 2014. We are grateful to Cheng Hsiao, Sergio Firpo, Marc Henry, Chuck Manski, Kevin Song, and Jeff Wooldridge for valuable comments and discussions. We thank Sang Mok Lee for excellent research assistance, and seminar participants at Michigan State, USC, U. Washington, the Canadian Econometrics Study Group meetings (2011, Toronto), and the Vanderbilt conference, Identification and Inference in Microeconometrics (2012) for useful comments. Formerly SSWP 1377.Attached Files
Published - Fan_2014p811.pdf
Files
Fan_2014p811.pdf
Additional details
Identifiers
- Eprint ID
- 45599
- Resolver ID
- CaltechAUTHORS:20140508-094952115
Related works
- Describes
- http://resolver.caltech.edu/CaltechAUTHORS:20170726-154328187 (URL)
Dates
- Created
-
2014-05-08Created from EPrint's datestamp field
- Updated
-
2021-11-10Created from EPrint's last_modified field