Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Spatial analysis›Spatial Panel Data Model (FE/RE)
Regression model

Spatial Panel Data Model (FE/RE)

Spatial Panel Data Model (Fixed and Random Effects) · Also known as: spatial panel FE/RE, spatial econometric panel, spatial lag/error panel, Uzamsal Panel Modeli (Spatial Panel FE/RE)

The spatial panel model is a family of econometric models that adds spatial dependence to panel data (units observed over time). It combines fixed- or random-effects panel structure with spatial lag, spatial error, or spatial Durbin components, and is developed in the modern spatial-econometrics literature by Elhorst (2014) and Lee & Yu (2010).

ScholarGate
  1. Regression model
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Spatial Panel Model
Geographically Weighted…Getis-Ord Gi*OLS RegressionPanel Fixed EffectsKrigingPanel Spatial Error ModelSpace-Time Spatial Autoc…Spatial Durbin ModelSpatial Error Model

When to use it

Use a spatial panel model when you have panel data (the same units measured over several periods), a continuous outcome, geographic coordinates or a defined neighbourhood structure, and a reasonable sample (at least about 100 observations). It is the right tool when outcomes plausibly spill over between neighbouring units, such as regional economic growth, housing prices, or environmental pollution. The ideal structure is large N with small-to-moderate T (a spatial micropanel). The spatial weight matrix W is usually assumed constant over time; choose between fixed and random effects with a Hausman test, and use LM tests to decide which spatial component (lag, error, or Durbin) is needed.

Strengths & limitations

Strengths
  • Captures spatial spillovers between neighbouring units that standard panel models ignore.
  • Flexible family: spatial lag, spatial error, and spatial Durbin specifications cover different spillover mechanisms.
  • Supports both fixed and random effects, so unobserved unit heterogeneity is controlled while modelling neighbourhood dependence.
Limitations
  • Cannot be applied without coordinates or a defined neighbourhood structure to build the spatial weight matrix W.
  • Results depend on the choice of W and the assumption that it is constant over time.
  • Dynamic specifications (with a lagged dependent variable) require bias-corrected LSDV or GMM estimation and are technically demanding (a high-difficulty method).

Frequently asked

How do I choose between fixed and random effects?

Use a Hausman test, exactly as in ordinary panel models. If the unit effects are correlated with the regressors, fixed effects are preferred; otherwise random effects are more efficient.

What is the difference between the spatial lag, error, and Durbin specifications?

The spatial lag model lets a unit's outcome depend on its neighbours' outcomes (ρ term); the spatial error model lets unobserved shocks be correlated across neighbours (λ term); the spatial Durbin model also adds spatially lagged predictors. LM tests help decide which component the data require.

What sample size and panel shape do I need?

At least about 100 observations, and the ideal structure is large N with small-to-moderate T — a spatial micropanel. The spatial weight matrix W is usually treated as constant over time.

What if my data has no coordinates?

Without coordinates or a defined neighbourhood structure you cannot build the spatial weight matrix W, so a spatial panel model cannot be applied. Use a standard fixed-effects panel model instead.

Sources

  1. Elhorst, J. P. (2014). Spatial Econometrics: From Cross-Sectional Data to Spatial Panels. Springer. DOI: 10.1007/978-3-642-40340-8 ↗
  2. Lee, L. F., & Yu, J. (2010). Estimation of Spatial Autoregressive Panel Data Models with Fixed Effects. Journal of Econometrics, 154(2), 165–185. DOI: 10.1016/j.jeconom.2009.08.001 ↗

How to cite this page

ScholarGate. (2026, June 1). Spatial Panel Data Model (Fixed and Random Effects). ScholarGate. https://scholargate.app/en/spatial-analysis/spatial-panel-model

Related methods

Geographically Weighted RegressionGetis-Ord Gi*OLS RegressionPanel Fixed Effects

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Geographically Weighted RegressionSpatial analysis↔ compare
  • Getis-Ord Gi*Spatial analysis↔ compare
  • OLS RegressionEconometrics↔ compare
  • Panel Fixed EffectsEconometrics↔ compare
Compare side by side →

Referenced by

KrigingPanel Spatial Error ModelSpace-Time Spatial AutocorrelationSpatial Durbin ModelSpatial Error Model

Similar methods

Global Spatial Panel ModelPanel Spatial RegressionPanel Spatial Durbin ModelSpace-Time Spatial Panel ModelPanel Spatial Error ModelSpace-Time Spatial RegressionSpace-Time Spatial Error ModelSpace-Time Spatial Lag Model

Related reference concepts

Panel Data Models • Spatio-temporal ModelsPanel Data Models • Spatio-temporal ModelsMultiple or Simultaneous Equation Models • Multiple VariablesCross-Sectional Models • Spatial Models • Treatment Effect Models • Quantile RegressionsCross-Sectional Models • Spatial Models • Treatment Effect Models • Quantile Regressions • Social Interaction ModelsEconometrics

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Spatial Panel Model (Spatial Panel Data Model (Fixed and Random Effects)). Retrieved 2026-07-21 from https://scholargate.app/en/spatial-analysis/spatial-panel-model · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Elhorst; Lee & Yu
Year
2014
Type
Spatial econometric panel model
Estimator
Maximum likelihood / bias-corrected LSDV (GMM for dynamic models)
Outcome
continuous
DataStructure
panel (unit × time)
MinSample
100
Related methods
Geographically Weighted RegressionGetis-Ord Gi*OLS RegressionPanel Fixed Effects
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account