Journal | Labour Economics |
---|
Date | Accepted/In press - 13 Jun 2016 |
---|
Date | E-pub ahead of print - 25 Jun 2016 |
---|
Date | Published (current) - Aug 2016 |
---|
Volume | 41 |
---|
Number of pages | 13 |
---|
Pages (from-to) | 47-60 |
---|
Early online date | 25/06/16 |
---|
Original language | English |
---|
This paper provides an introduction into the estimation of marginal treatment effects (MTE). Compared to the existing surveys on the subject, our paper is less technical and speaks to the applied economist with a solid basic understanding of econometric techniques who would like to use MTE estimation. Our framework of analysis is a generalized Roy model based on the potential outcomes framework, within which we define different treatment effects of interest, and review the well-known case of IV estimation with a discrete instrument resulting in a local average treatment effect (LATE). Turning to IV estimation with a continuous instrument, we demonstrate that the 2SLS estimator may be viewed as a weighted average of LATEs and discuss MTE estimation as an alternative and more informative way of exploiting a continuous instrument. We clarify the assumptions underlying the MTE framework, its relation to the correlated random coefficients model, and illustrate how the MTE estimation is implemented in practice.
© 2016 Elsevier B.V. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.