Using generalized estimating equations to estimate nonlinear models with spatial data

TL;DR

This paper introduces a two-step GEE method for estimating nonlinear spatial models, improving efficiency by accounting for spatial correlation, with applications to count and binary data, including FDI inflow analysis.

Contribution

It proposes a grouping estimator within the GEE framework to better handle spatial correlation in nonlinear models, demonstrating efficiency gains over existing methods.

Findings

Efficiency improvements shown in Monte Carlo simulations.

Successful application to FDI inflow determinants.

Establishment of consistency and asymptotic normality under weak dependence.

Abstract

In this paper, we study estimation of nonlinear models with cross sectional data using two-step generalized estimating equations (GEE) in the quasi-maximum likelihood estimation (QMLE) framework. In the interest of improving efficiency, we propose a grouping estimator to account for the potential spatial correlation in the underlying innovations. We use a Poisson model and a Negative Binomial II model for count data and a Probit model for binary response data to demonstrate the GEE procedure. Under mild weak dependency assumptions, results on estimation consistency and asymptotic normality are provided. Monte Carlo simulations show efficiency gain of our approach in comparison of different estimation methods for count data and binary response data. Finally we apply the GEE approach to study the determinants of the inflow foreign direct investment (FDI) to China.