Endogeneity and education returns

Abstract

Based on the fact that the non-fulfilment of the exogeneity assumption on education in an earning function produces inconsistent OLS estimates, the object of this article is to show a set of procedures, mainly based on the use of instrumental variables, to estimate the return to education in Mexico considering that schooling is endogenous. The general result is that returns are notably increased, what might be showing the return of specific groups of population with financial restrictions and a higher return with respect to the average return. The data base used were the Household Budget Survey, 1994 and 1996.