Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/76216 
Authors: 
Year of Publication: 
2010
Series/Report no.: 
Working Paper No. 1001
Publisher: 
University of Zurich, Socioeconomic Institute, Zurich
Abstract: 
This paper analyzes the identifying power of weak convexity assumptions in treatment effect models with endogenous selection. The counterfactual distributions are constrained either in terms of the response function, or conditional on the realized treatment, and sharp bounds on the potential outcome distributions are derived. The methods are applied to bound the effect of education on smoking.
Subjects: 
nonparametric bounds
causality
endogeneity
instrumental variables
JEL: 
C14
C30
I12
Document Type: 
Working Paper

Files in This Item:
File
Size
252.32 kB





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