Document Type
Working Paper
Publication Date
Summer 7-2013
College/Unit
Chambers College of Business and Economics
Document Number
13-01
Department/Program/Center
Economics
Abstract
An interesting puzzle in estimating the effect of education on labor market earnings (Card (2001)) is that the 2SLS estimate for the return to schooling typically exceeds the OLS estimate, but the 2SLS estimate is fairly imprecise. We provide a new explanation that it could be due to the restrictive linear functional form specification on the control variables and the reduced form. For the parameters of endogenous regressors, we propose two kernel-based semiparametric IV estimators that relax the tight functional form assumption on the control variables and the reduced form. They have explicit algebraic structures and are easily implemented without numerical optimizations. We show that they are consistent, asymptotically normally distributed, and reach the semiparametric efficiency bound. A Monte Carlo study demonstrates that our estimators perform well in finite samples. We apply the proposed estimators to estimate the return to schooling in Card (1995). We find that the semiparametric estimates of the return to schooling are much smaller and more precise than the 2SLS estimate, and the difference largely comes from the misspecification in the linear reduced form.
Digital Commons Citation
Yao, Feng and Zhang, Junsen, "Efficient kernel-based semiparametric IV estimation with an application to resolving a puzzle on the estimates of the return to schooling" (2013). Economics Faculty Working Papers Series. 81.
https://researchrepository.wvu.edu/econ_working-papers/81