Robust estimation for spatially varying-coefficient models

doi:10.1007/s00362-025-01796-6

Robust estimation for spatially varying-coefficient models

2026-02-06

0

PRE

AI

DOI：10.1007/s00362-025-01796-6

Original

Original request for help

Save

Abstract

En 中文

Spatially varying-coefficient models (SVCMs) are a classical statistical tool designed to address non-stationary relationships between variables across geographic space. Existing estimation methods for SVCMs are all based on ordinary least squares (OLS), which are not robust to outliers in response measurements or heavy-tailed error distributions. To address this issue, in this paper we propose a robust estimation approach for SVCMs using bivariate spline approximation technique. We establish the consistency and asymptotic normality of the proposed estimator. The proposed method is further illustrated by simulation studies which demonstrate the finite sample performance of the method, and is applied in an empirical analysis.

Keywords:

Bivariate spline

Irregular domain

Robust estimation

Spatial data

Triangulation

Varying-coefficient models

Robust estimation for spatially varying-coefficient models

Abstract

Journal

Organization