No. 1210 - Identification and estimation of triangular models with a binary treatment

Vai alla versione italiana Site Search

by Santiago Pereda FernándezMarch 2019

This paper studies the identification of econometric models that assess the effects of a binary treatment, comparing the outcome of interest between treated and untreated individuals. It proposes an estimator that makes it possible to estimate the marginal treatment effect and a methodology for decomposing the differences in outcome between treated and untreated individuals.

The model proposed makes it possible to identify a greater amount of heterogeneous effects compared with existing models, enabling a better characterization of the effects of the treatment. As an application, it studies the effects of a program that helps unemployed workers to find a job. The results indicate that finding a job quickly has a positive effect on workers' future earnings, although this effect is heterogeneous.

Full text