Inequality Impacts of Raising Minimum Years of Schooling

In this paper, we present a new, flexible method for estimating the impact on the parameters of the distribution that can be expressed as raw moments, such as the variance (E[Y^2] − E[Y]^2) of outcome Y and the covariance (E[YH] − E[Y]E[H]) of two outcomes Y and H. Our approach involves predicting the observed and counterfactual values for each expectation (E(Y^2), E(Y), E(YH), E(H)) using standard causal regressions.

We then combine these predictions to estimate a policy’s impact on the parameters of interest. Our new approach is as good as existing approaches under selection on observables. To demonstrate the usefulness of our method, we go beyond the limits of current approaches and extend the analysis to where there is selection on unobservables considering a difference-in-differences set-up for a major Swedish reform that increased the minimum years of schooling.

Our results show that this reform reduced the variance in years of schooling. Moving forward, we plan to estimate the impact of this reduction in education inequality on the variance of labour income between 30-40-year-olds and the covariance of earned labour income and mortality.

Online attendance

Interested individuals should contact healtheconomics@ese.eur.nl if they would like to attend the seminar virtually.