Bayesian estimation for partially linear varying coefficient spatial autoregressive models

Abstract

We propose a fully Bayesian estimation approach for partially linear varying coefficient spatial autoregressive models on the basis of B-spline approximations of nonparametric components. A computational efficient MCMC method that combines the Gibbs sampler with Metropolis-Hastings algorithm is implemented to simultaneously obtain the Bayesian estimates of unknown parameters, as well as their standard error estimates. Monte Carlo simulations are used to investigate the finite sample performance of the proposed method. Finally, a real data analysis of Boston housing data is used to illustrate the usefulness of the proposed methodology.

Variable Selection of High-Dimensional Spatial Autoregressive Panel Models with Fixed Effects

“…Du et al [8] proposed the estimator for the asymptotic covariance matrix of the parameter estimator of partially linear additive SAR models and established the asymptotic properties for the resulting estimators. Other research results on SAR models can also be referred to Cheng et al [9], Dai et al [10], Gupta and Robinson [11], Lin and Lee [12], Tian et al [13], Tian et al [14], and so on. Tese studies based on cross-sectional data are not applicable to panel data, and variable selection is rarely involved.…”