Premium
Comparaison des caractéristiques des estimateurs pratiques pour les modèles de choix binaires avec régresseurs endogènes .
Author(s) -
Lewbel Arthur,
Dong Yingying,
Yang Thomas Tao
Publication year - 2012
Publication title -
canadian journal of economics/revue canadienne d'économique
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.773
H-Index - 69
eISSN - 1540-5982
pISSN - 0008-4085
DOI - 10.1111/j.1540-5982.2012.01733.x
Subject(s) - estimator , heteroscedasticity , control function , binary number , econometrics , m estimator , statistics , function (biology) , mathematics , computer science , control (management) , artificial intelligence , evolutionary biology , biology , arithmetic
We discuss the relative advantages and disadvantages of four types of convenient estimators of binary choice models when regressors may be endogenous or mismeasured or when errors are likely to be heteroscedastic. For example, such models arise when treatment is not randomly assigned and outcomes are binary. The estimators we compare are the two‐stage least squares linear probability model, maximum likelihood estimation, control function estimators, and special regressor methods. We specifically focus on models and associated estimators that are easy to implement. Also, for calculating choice probabilities and regressor marginal effects, we propose the average index function (AIF), which, unlike the average structural function (ASF), is always easy to estimate.