A Generalized Moments Estimator for the Autoregressive Parameter in a Spatial Model

TLDR

The paper addresses estimating the autoregressive parameter in a common spatial autocorrelation model, where the usual (quasi) maximum likelihood estimator based on a normal density is often used. The authors propose a generalized moments estimator that remains computationally simple regardless of sample size. They develop this estimator by applying a generalized moments framework that can be computed efficiently for any sample size. The study shows that the quasi‑maximum likelihood estimator can be computationally infeasible for moderate or large samples, and it presents large‑ and small‑sample properties of the proposed generalized moments estimator.

Abstract

This paper is concerned with the estimation of the autoregressive parameter in a widely considered spatial autocorrelation model. The typical estimator for this parameter considered in the literature is the (quasi) maximum likelihood estimator corresponding to a normal density. However, as discussed in this paper, the (quasi) maximum likelihood estimator may not be computationally feasible in many cases involving moderate‐ or large‐sized samples. In this paper we suggest a generalized moments estimator that is computationally simple irrespective of the sample size. We provide results concerning the large and small sample properties of this estimator.