← Search

Please Call Again: Correcting Nonresponse Bias in Treatment Effect Models

Luc Behaghel1; Bruno Crépon2; Marc Gurgand3,1; Thomas Le Barbanchon

1 Paris School of Economics · 2 CREST · 3 Centre National de la Recherche Scientifique

The Review of Economics and Statistics 2015 open access

We propose a novel selectivity correction procedure to deal with survey attrition in treatment effect models, at the crossroads of the Heckit model and the bounding approach of Lee (2009). As a substitute for the instrument needed in sample selectivity correction models, we use information on the number of prior calls made to each individual before obtaining a response to the survey. We obtain sharp bounds to the average treatment effect on the common support of responding individuals. Because the number of prior calls brings information, we can obtain tighter bounds than in other nonparametric methods.

DOI
10.1162/rest_a_00497
Volume
97 (5)
Pages
1070-1080
Language
en
Export
BibTeX
Sources
openalex crossref