Impact evaluation of job training programs by a latent variable model

We introduce a model for categorical panel data which is tailored to the dynamic evaluation of the impact of job training programs. The model may be seen as an extension of the dynamic logit model and, as such, it allows us to disentangle true from spurious state dependence. The unobserved heterogeneity between subjects is taken into account by formulating the conditional distribution of the response variables given a discrete latent variable. For the estimation of the model parameters we use an EM algorithm and we compute standard errors on the basis of the numerical derivative of the score vector of the complete data log-likelihood. The approach is illustrated through the analysis of a dataset containing the work histories of the employees of the private rms of the province of Milan between 2003 and 2005, some of whom attended job training programs supported by the European Social Fund.