Simple Estimators for Treatment Parameters in a Latent Variable Framework with an Application to Estimating the Returns to Schooling

James J. Heckman, Justin L. Tobias, Edward Vytlacil

NBER Working Paper No. 7950
Issued in October 2000
NBER Program(s):   CH   LS   PE

This paper derives simply computed closed-form expressions for the Average Treatment Effect (ATE), the effect of Treatment on the Treated (TT), Local Average Treatment Effect (LATE) and Marginal Treatment Effect (MTE) in a latent variable framework for both normal and non-normal models. The techniques presented in the paper are applied to estimating a variety of treatment parameters capturing the returns to a college education for various populations using data from the National Longitudinal Survey of Youth (NLSY).

(1587 K)

Published: Heckman, James J., Justin L. Tobias, and Edward Vytlacil. "Simple Estimators for Treatment Parameters within a Latent Variable Framework." Review of Economics and Statistics 85, 3 (2003).

This paper is available as PDF (1587 K) or via email.

Machine-readable bibliographic record - MARC, RIS, BibTeX