A bivariate marginal likelihood specification of spatial econometric modeling of very large datasets

TL;DR

This paper introduces a bivariate marginal likelihood approach for spatial econometric models that simplifies estimation, avoids arbitrary weight matrix choices, and offers analytical and computational benefits for large datasets.

Contribution

It presents a novel likelihood specification that streamlines estimation and interpretation in spatial econometrics, especially for very large datasets.

Findings

Provides a closed-form expression for parameter estimation.

Establishes small sample and asymptotic properties of estimators.

Derives Fisher information matrix for inference.

Abstract

This paper proposes a bivariate marginal likelihood specification of spatial econometrics models that simplifies the derivation of the log-likelihood and leads to a closed form expression for the estimation of the parameters. With respect to the more traditional specifications of spatial autoregressive models, our method avoids the arbitrariness of the specification of a weight matrix, presents analytical and computational advantages and provides interesting interpretative insights. We establish small sample and asymptotic properties of the estimators and we derive the associated Fisher information matrix needed in confidence interval estimation and hypothesis testing.