Abstract:
What follows is an exercise aimed at estimating private vs. public school effect on academic achievement. It is based on the analysis of Math, Science and Reading test scores of 15 year-olds students surveyed in 2002 across OECD and non-OECD countries. Its main purpose is to get an accurate measure of the achievement differentials of students that have chosen to attend private and public schools. To do so, it is absolutely necessary to control for all exogenous factors that influence outcome and have nothing to do with a private/public effectiveness differential. We henceforth control for different types of bias: the student and the student’s peer group (observed) socio-economic background, but also variables that are not observed by the statistician (like motivation). The latter is done using an endogenous treatment model derived from Heckman’s two-stages approach of endogeneity/selectivity. Estimations show that the effect of a private education varies across countries: in a first group of country, students from private schools perform better. In a second group, there is no distinct effect of a public/private education. Finally, in a third, smaller group, public schools seem to outperform private ones.