CORRELATED RANDOM EFFECTS MODELSWITH UNBALANCED PANELSJeffrey M. Wooldridge∗Department of EconomicsMichigan State UniversityEast Lansing, MI 48824-1038[email protected]July 2009∗I presented an earlier version of this paper, called “Nonlinear Correlated Random EffectsModels with Unbalanced Panels,” at the 15thConference on Panel Data, Bonn, Germany,July 3-5, 2009. I thank Simon Quinn for helpful comments.1
has intentionally blurred sections.
Sign up to view the full version.
Abstract: I propose some strategies for allowing unobserved heterogeneity to be correlatedwith observed covariates and sample selection for unbalanced panels. The methods areextensions of the Chamberlain-Mundlak approach for balanced panels. Even for nonlinearmodels, in many cases the estimators can be implemented using standard software. Theframework suggests straightforward tests of correlation between heterogeneity and thecovariates, as well as sample selection that is correlation with unobserved shocks whileallowing selection to be correlated with the observed covariates and unobserved heterogeneity.2