Average effect of training programs on the time needed to find a job. The case of the training schools program in the south of Spain (Seville, 1997-1999)

Abstract

This paper estimes the average effect of a binary treatment on a scalar outcome. Such a treatment is the training schools program implemented in the South of Spain (Seville) between 1997 and 1999. Speciffically, the paper estimes the average effect of this training program on the time needed to find a job. Difficulty in accesing microdata has obstructed in Spain this type of evaluation, largely developed in France, Germany, United Kingdom and USA. For our purpose, two methods based on the previous estimation of the propensity score are applied: weighting observations by the inverse of the propensity score and Heckman’s “twostage” estimator -Heckman (1979)-. The average effect estimed by weighting observations by the inverse of a nonparametric estime of the propensity score let us to conclude that, for treated, the time needed to find a job is reduced in 471 days. With the second method authors conclude that the estimator of ATET (α ATET ˆ ) takes a positive value -446 days -although minor than the previous one.