A0558
Title: Nonparametric estimation of smooth coefficients in fixed-effect panel data models
Authors: Taining Wang - Capital University of Economics and Business (China) [presenting]
Feng Yao - West Virginia University (United States)
Jun Cai - Huazhong University of Science and Technology (China)
Abstract: A kernel-based nonparametric estimator is proposed for a smooth coefficient panel data model with fixed effects. Without requiring a zero sum of fixed effects, an estimator is proposed that is easy to construct and computationally efficient. Eliminating the fixed effects through a local within transformation, a local linear estimation is performed for the coefficient functions associated with time-varying variables. The intercept coefficient function is further estimated, if present, through a difference of kernel weighted averages. The estimator's asymptotic properties are characterized under a large-$n$ and large-$T$ framework. It is demonstrated that the estimator is not asymptotically equivalent to the standard kernel estimator that ignores fixed effects. Through extensive simulation studies, the estimator's encouraging numerical performance and computational advantages are highlighted over existing kernel estimators in the literature. The empirical applicability is showcased by investigating a varying coefficient version of the environmental Kuznets curve through a panel of OECD countries.
