Spatial Econometrics

Manfred M. Fischer and James P. LeSage

No 2, Working Papers in Regional Science from WU Vienna University of Economics and Business

Abstract: Spatial econometrics deals with econometric modeling in the presence of spatial dependence and heterogeneity, where observations correspond to specific spatial units such as points or regions. Traditional estimation techniques assume independent observations and are inadequate when spatial dependence exists. This article provides an overview of spatial econometric models, highlighting the challenges posed by spatial dependence in cross-sectional data. It examines key models, including the Spatial Autoregressive (SAR), Spatial Error (SEM), and Spatial Durbin (SDM) models, while detailing maximum likelihood estimation (MLE) techniques and computational advancements for handling large datasets. Alternative estimation approaches, such as the generalized method of moments, Bayesian methods, non-parametric locally linear models, and matrix exponential spatial models, are also discussed. The article explores methods applicable to continuous, dichotomous, and censored variables. Interpreting spatial regression model estimates correctly is crucial for drawing valid inferences. Distinguishing between direct, indirect (spillover), and total effects and careful specification of the spatial weight matrix is essential. Misinterpretation can lead to flawed conclusions, undermining policy relevance – especially when assessing interventions with potential spillovers. By adhering to rigorous interpretation practices, researchers can fully leverage spatial regression models while mitigating analytical pitfalls.

Keywords: Bayesian methods; censored dependent models; cross-sectional models; generalized method of moments; marginal effects; matrix exponential spatial models; maximum likelihood; non-parametric locally linear models; spatial dependence; spillover effects (search for similar items in EconPapers)
Date: 2025
New Economics Papers: this item is included in nep-dcm
References: Add references at CitEc
Citations:

Downloads: (external link)
https://research.wu.ac.at/en/publications/1019c1c5-41ba-4ffc-a61f-0c645889aa3b original version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wiw:wus046:72854367

Access Statistics for this paper

More papers in Working Papers in Regional Science from WU Vienna University of Economics and Business Welthandelsplatz 1, 1020 Vienna, Austria.
Bibliographic data for series maintained by WU Library ().