Premium
Endogenous treatment effects for count data models with endogenous participation or sample selection
Author(s) -
Bratti Massimiliano,
Miranda Alfonso
Publication year - 2011
Publication title -
health economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.55
H-Index - 109
eISSN - 1099-1050
pISSN - 1057-9230
DOI - 10.1002/hec.1764
Subject(s) - endogeneity , count data , econometrics , outcome (game theory) , average treatment effect , economics , sample (material) , selection (genetic algorithm) , estimator , margin (machine learning) , selection bias , instrumental variable , estimation , endogeny , treatment effect , statistics , medicine , microeconomics , computer science , mathematics , chemistry , management , chromatography , artificial intelligence , machine learning , poisson distribution , traditional medicine
Abstract In this paper, we propose an estimator for models in which an endogenous dichotomous treatment affects a count outcome in the presence of either sample selection or endogenous participation using maximum simulated likelihood. We allow for the treatment to have an effect on the participation or the sample selection rule and on the main outcome. Applications of this model are frequent in–but no limited to–health economics. We show an application of the model using data from Kenkel and Terza (2001), who investigate the effect of physician advice on the amount of alcohol consumption. Our estimates suggest that in these data (i) neglecting treatment endogeneity leads to a wrongly signed effect of physician advice on drinking intensity, (ii) accounting for treatment endogeneity but neglecting endogenous participation leads to an upward biased estimate of the treatment effect and (iii) advice affects only the drinking intensive margin but not drinking prevalence. Copyright © 2011 John Wiley & Sons, Ltd.