Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/253607 
Year of Publication: 
2021
Citation: 
[Journal:] Quantitative Economics [ISSN:] 1759-7331 [Volume:] 12 [Issue:] 4 [Publisher:] The Econometric Society [Place:] New Haven, CT [Year:] 2021 [Pages:] 1197-1221
Publisher: 
The Econometric Society, New Haven, CT
Abstract: 
We analyze the properties of the Synthetic Control (SC) and related estimators when the pre-treatment fit is imperfect. In this framework, we show that these estimators are generally biased if treatment assignment is correlated with unobserved confounders, even when the number of pre-treatment periods goes to infinity. Still, we show that a demeaned version of the SC method can improve in terms of bias and variance relative to the difference-in-difference estimator. We also derive a specification test for the demeaned SC estimator in this setting with imperfect pre-treatment fit. Given our theoretical results, we provide practical guidance for applied researchers on how to justify the use of such estimators in empirical applications.
Subjects: 
Synthetic control
difference-in-differences
policy evaluation
linearfactor model
JEL: 
C13
C21
C23
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc Logo
Document Type: 
Article

Files in This Item:
File
Size
366.4 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.