Premium
The Nonparametric Identification of Treatment Effects in Duration Models
Author(s) -
Abbring Jaap H.,
Van Den Berg Gerard J.
Publication year - 2003
Publication title -
econometrica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 16.7
H-Index - 199
eISSN - 1468-0262
pISSN - 0012-9682
DOI - 10.1111/1468-0262.00456
Subject(s) - econometrics , covariate , identification (biology) , observational study , duration (music) , nonparametric statistics , outcome (game theory) , anticipation (artificial intelligence) , multivariate statistics , spell , instrumental variable , computer science , statistics , mathematics , machine learning , botany , biology , art , literature , mathematical economics , sociology , anthropology
This paper analyzes the specification and identification of causal multivariate duration models. We focus on the case in which one duration concerns the point in time a treatment is initiated and we are interested in the effect of this treatment on some outcome duration. We define “no anticipation of treatment” and relate it to a common assumption in biostatistics. We show that (i) no anticipation and (ii) randomized treatment assignment can be imposed without restricting the observational data. We impose (i) but not (ii) and prove identification of models that impose some structure. We allow for dependent unobserved heterogeneity and we do not exploit exclusion restrictions on covariates. We provide results for both single‐spell and multiple‐spell data. The timing of events conveys useful information on the treatment effect.