Nonparametric Slope Estimators for Fixed-Effect Panel Data

Abstract:     
In panel data the interest often is in slope estimation while taking account of the unobserved cross sectional heterogeneity. Firstly, this paper proposes two nonparametric slope estimators where the unobserved cross-sectional effect is treated as fixed. The first estimator uses a first-differencing transformation and the second estimator uses a mean deviation transformation. The asymptotic properties of the two estimators are established and the finite sample Monte Carlo properties of the two estimators are investigated allowing for systematic dependence between the cross-sectional effect and the independent variable. Simulation results suggest that the new nonparametric estimators perform better than the parametric counterparts. Secondly, the small sample Monte Carlo comparing the parametric within and first differencing estimators are presented. Finally, a very common practice in estimating earning function is to assume earnings to be quadratic in age and tenure, but that might be misspecified. In this paper, as an empirical illustration, we estimate nonparametric slope of age and tenure on earnings using NLSY data and compare it to the parametric (quadratic) slope.

Keywords: Nonparametric, Fixed-effect, Kernel, Monte Carlo

JEL Classification: C1, C14, C23, C15

working papers series