Affordable Access

Monotonicity and the Roy model

Centre for the Economics of Education, London School of Economics and Political Science
Publication Date
  • Hb Economic Theory
  • Education


CEE DP28 READY3july02.doc Monotonicity and the Roy Model Arnaud Chevalier and Gauthier Lanot June 2002 Published by Centre for the Economics of Education London School of Economics and Political Science Houghton Street London WC2A 2AE Ó Arnaud Chevalier and Gauthier Lanot, submitted June 2002 ISBN 0 7530 1532 3 Individual copy price: £5 The Centre for the Economics of Education is an independent research centre funded by the Department for Education and Skills. The views expressed in this work are those of the authors and do not necessarily reflect the views of the DfES. All errors and omissions remain the authors. Executive Summary In the context of the returns to education literature, this note compares the restrictions imposed by two selection models, the Roy model and Monotone Treatment Selection, as proposed by Manski and Pepper. While researchers agree that average individual earnings increase with years of schooling,the causality of this association as well as its magnitude is a subject of debate. Various econometric methods (twins, IV) have been used to calculate the returns to education, biased by the non-observability of various determinants that also determine earnings (such as ability) and mis-measurement error. However, these methods impose various assumptions. Recently, several authors have attempted to characterise the magnitude of the returns to education without imposing such constraints. Here, we concentrate on the non-parametric estimates proposed by Manski and Pepper (2000). Following Manski (1990) which relies solely on the distributions of the treatment and outcome variables to estimate bounds rather than point estimates, Manski and Pepper (2000) impose a set of restriction: monotonicity in t

There are no comments yet on this publication. Be the first to share your thoughts.


Seen <100 times