Selectivity bias arises in program evaluation when the treatment or control status of the subjects is related to unmeasured characteristics that themselves are related to the program outcome under study. This situation has the potential to lead to an incorrect estimation of the treatment effect when assignment to treatment and control groups is not random. This paper adopts techniques that were recently developed in the econometric analysis of labor and markets and applies these techniques in order to resolve the bias problem of conventional evaluation models. The selection bias problem is placed in a broader context by considering references to the institutional setting of evaluation research and to its application in labor economies. The paper concludes with several caveats about the proposed technique. (Author/MK)