Dynamic Spatial Autoregressive Models with Autoregressive and Heteroskedastic Disturbances

TL;DR

This paper introduces a novel class of dynamic spatial autoregressive models that incorporate time-varying coefficients and heteroskedastic disturbances, enhancing the analysis of complex spatio-temporal data.

Contribution

It generalizes the SARAR(1,1) model using Score Driven methods to allow for dynamic parameters and heteroskedasticity, with extensive simulation and application to portfolio optimization.

Findings

Maximum Likelihood estimator performs well in finite samples

Models effectively capture dynamic spatial dependence

Economically preferred in portfolio optimization

Abstract

We propose a new class of models specifically tailored for spatio-temporal data analysis. To this end, we generalize the spatial autoregressive model with autoregressive and heteroskedastic disturbances, i.e. SARAR(1,1), by exploiting the recent advancements in Score Driven (SD) models typically used in time series econometrics. In particular, we allow for time-varying spatial autoregressive coefficients as well as time-varying regressor coefficients and cross-sectional standard deviations. We report an extensive Monte Carlo simulation study in order to investigate the finite sample properties of the Maximum Likelihood estimator for the new class of models as well as its flexibility in explaining several dynamic spatial dependence processes. The new proposed class of models are found to be economically preferred by rational investors through an application in portfolio optimization.