evaluation , active labor market programs , dynamic non–linear panel data models , MCMC
Abstract:
This paper estimates the impact of training incidence and duration on employment transitions accounting for the endogeneity of program participation and duration. We specify a very flexible bivariate random effects probit model for employment and training participation and we use Bayesian Markov Chain Monte Carlo (MCMC) techniques for estimation. We develop a simulation approach that uses the estimated coefficients and individual specific effects from the MCMC iterations to calculate the posterior distributions of different treatment effects of interest. Our estimation results imply positive effects of training on the employment probability of the treated, lying between 12 and 21 percentage points ten quarters after program start. The effects are higher for women than for men and higher in West Germany than in East Germany. Further, we find that the effect of training versus waiting underestimates the effect of training versus no training in the medium and long run by a third. Finally, our results show that longer planned enrolment lengths of three and four quarters as opposed to just two quarters lead to an increase in employment rates in the medium and long run by four to eleven percentage points.
Additional information:
Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.
![[img]](https://madoc.bib.uni-mannheim.de/style/images/fileicons/application_pdf.png)
Search Authors in
