The review found that the Heckman estimators tended to be used mechanistically, without sufficient attention to the particular circumstances related to sample selection. The Heckman estimator is only appropriate for estimating a theoretical model of a particular kind of selection. Different selection processes require different modeling approaches, which in turn require different estimators. The review also found significant problems with the way the Heckman estimator had been applied in the majority of the studies reviewed. These errors included the use of the logit rather than probit in the first stage, the use of models other than OLS in the second stage, failure to correct heteroskedastic errors, and improper calculation of the inverse Mills ratio. Collectively these errors raise serious questions about the validity of prior results derived from miscalculated or misapplied versions of Heckman's correction for selection bias. Even when the correction has been properly implemented, however, research evidence shows that the Heckman approach can seriously inflate standard errors due to collinearity between the correction term and the included regressors. This problem is intensified in the absence of exclusion restrictions. These are variables that affect the selection process but not the substantive equation of interest. The review concludes by highlighting two approaches that provide important intuition regarding the severity of sample selection bias and the potential benefits of correcting it with Heckman's technique. 3 figures, 3 tables, and 94 references