Foul or fair? : the Heckman correction for sample selection and its critique; a short survey

This paper gives a short overview of Monte Carlo studies on the usefulness of Heckman's (1976, 1979) twostep estimator for estimating a selection model. It shows that exploratory work to check for collinearity problems is strongly recommended before deciding on which estimator to apply. In the absence of collinearity problems, the fullinformation maximum likelihood estimator is preferable to the limitedinformation twostep method of Heckman, although the latter also gives reasonable results. If, however, collinearity problems prevail, subsample OLS (or the TwoPart Model) is the most robust amongst the simpleto calculate estimators.