EcoSta 2019: Start Registration
View Submission - EcoSta2019
Title: A varying coefficient panel data model with random individual effect and spatial errors Authors:  Pipat Wongsa-art - Cardiff University (United Kingdom) [presenting]
Abstract: A varying coefficient panel data model with error components that are both spatially and time-wise correlated is considered. The model blends specifications typically considered in the spatial literature with those considered in the error components literature. We introduce the maximum likelihood estimators for estimating the spatial autoregressive parameter and the variance components of the disturbance process, which can be considered a generalized counterpart to the moments estimators suggested previously, within the non-varying coefficient context. We then use these estimators in the construction of the Nadaraya-Watson type estimation of the varying coefficient model. Nevertheless, how to conduct variable selection for the varying coefficient model in a computationally efficient manner is poorly understood. To solve the problem, we follow existing works, which combines the ideas of the local polynomial smoothing and the Least Absolute Shrinkage and Selection Operator, and presents new asymptotic results.