On the Estimation of Selection Models When Participation is Endogenous and Misclassified
McCarthy, I. and R. Tchernis. 2011. “On the Estimation of Selection Models when Participation is Endogenous and Misclassified,” in D. Drukker (Ed.), Advances in Econometrics, Missing-Data Methods: Cross-sectional Methods and Applications 27:179-207. London: Emerald Group Publishing.
34 Pages Posted: 30 Nov 2010 Last revised: 13 Feb 2015
Date Written: November 1, 2010
This paper presents a Bayesian analysis of the endogenous treatment model with misclassifed treatment participation. Our estimation procedure utilizes a combination of data augmentation, Gibbs sampling, and Metropolis-Hastings to obtain estimates of the misclassifcation probabilities and the treatment effect. Simulations demonstrate that the proposed Bayesian estimator accurately estimates the treatment effect in light of misclassifcation and endogeneity.
Keywords: Misclassification, Misreporting, Endogeneity, Selection on Observables, Measurement Error, Bayesian Econometrics
JEL Classification: C31, C35, C51, C52
Suggested Citation: Suggested Citation