In this paper we have proposed a methodology to predict future labour market outcomes for students still in school, surveyed by the PISA programme. This is made possible by the existence of another survey conducted in the adult population, reporting comparable information on interviewees backgrounds (in addition to gender, age and country of origin, we consider parental education and family educational resources). Using coarsened exact matching technique, we impute adult numeracy and literacy, which are then used to predict hourly wages and employment probabilities. In order to highlight the working of our model, we run a counterfactual experiment where we reduce the student/teacher ratio in schools, showing the likely impact on expected wage inequality 25 years later.
Can educational policies today change income inequality tomorrow?
PORRO, GIUSEPPE
2015-01-01
Abstract
In this paper we have proposed a methodology to predict future labour market outcomes for students still in school, surveyed by the PISA programme. This is made possible by the existence of another survey conducted in the adult population, reporting comparable information on interviewees backgrounds (in addition to gender, age and country of origin, we consider parental education and family educational resources). Using coarsened exact matching technique, we impute adult numeracy and literacy, which are then used to predict hourly wages and employment probabilities. In order to highlight the working of our model, we run a counterfactual experiment where we reduce the student/teacher ratio in schools, showing the likely impact on expected wage inequality 25 years later.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
