Premium
Semiparametric Binary Choice Panel Data Models Without Strictly Exogeneous Regressors
Author(s) -
Honoré Bo E.,
Lewbel Arthur
Publication year - 2002
Publication title -
econometrica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 16.7
H-Index - 199
eISSN - 1468-0262
pISSN - 0012-9682
DOI - 10.1111/1468-0262.00363
Subject(s) - honor , binary number , citation , computer science , library science , econometrics , mathematics , arithmetic , internet privacy
Most previous studies of binary choice panel data models with Þxed ef- fects require strictly exogeneous regressors, and except for the logit model without lagged dependent variables, cannot provide rate root n parameter estimates. We assume that one of the explanatory variables is independent of the individual speciÞc effect and of the errors of the model, conditional on the other explanatory variables. Based on Lewbel (2000a), we showhowthis alternative assumption can be used to identify and root-n consistently esti- mate the parameters of discrete choice panel data models with Þxed effects, only requiring predetermined (as opposed to strictly exogeneous) regressors. The estimator is semiparametric in that the error distribution is not speciÞed, and allows for general forms of heteroscedasticity.