Paolo Ghinetti (Università degli Studi del Piemonte Orientale) on "Heterogeneous Returns to Education in Italy: An Evaluation Based on Control Functions"

The estimation of economic average returns to education is  potentially subject to two selection issues: the so-called ‘ability bias’, responsible for the ‘endogeneity’ of education in earnings equations; and the ‘return bias’, due to heterogeneous returns to education which make individuals self-selecting into given education levels according to specific unobservable gains. A major limitation of the instrumental variables estimator (IV) used in many empirical applications is that it provides consistent estimates only if returns to education are homogeneous in the population, i.e. subject only to the ‘ability bias’. The aim of this paper is to use a simple control functions (CF) estimator to get consistent estimates of returns to schooling in a model which allows for heterogeneity in both ability and returns to education and which uses specific corrections terms included in the earnings equation(s) to control for them. We use data Bank of Italy data for Italian men in the 25-60 age interval. Identification is ensured by a major reform which in 1962 increased the number of years of compulsory schooling, and we use a set of cohort dummies as exclusion restrictions. Preliminary estimates find no evidence that more educated employees benefit on average from an absolute wage advantage. We also find evidence of positive self-selection: the more educated study more partly because their marginal return to education is higher than the average, due to specific unobservable gains from additional years of schooling.