Identification and Estimation of Regression Models with Misclassification

38 Pages Posted: 10 Jan 2010

See all articles by Aprajit Mahajan

Aprajit Mahajan

University of California, Berkeley - Department of Agricultural & Resource Economics; Stanford University; National Bureau of Economic Research (NBER)

Date Written: December 1, 2005

Abstract

This paper studies the problem of identification and estimation in nonparametric regression models with a misclassified binary regressor where the measurement error may be correlated with the regressors. We show that the regression function is non-parametrically identified in the presence of an additional random variable that is correlated with the unobserved true underlying variable but unrelated to the measurement error. Identification for semi-parametric and parametric regression functions follows straightforwardly from the basic identification result. We propose a kernel estimator based on the identification strategy and derive its large sample properties and also discuss alternative estimation procedures.

Keywords: Non-Classical Measurement Error, Non-Linear Models, Identification, Misclassification

JEL Classification: C2

Suggested Citation

Mahajan, Aprajit, Identification and Estimation of Regression Models with Misclassification (December 1, 2005). Econometrica Vol. 74, No. 3, pp. 631-665, 2006, Available at SSRN: https://ssrn.com/abstract=1533689

Aprajit Mahajan (Contact Author)

University of California, Berkeley - Department of Agricultural & Resource Economics ( email )

Berkeley, CA 94720
United States

Stanford University ( email )

Stanford, CA 94305
United States

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States