45 Citations (Scopus)

Abstract

We investigate the common conjecture in applied econometric work that the inclusion of spatial fixed effects in a regression specification for a single cross-sectional data set removes spatial dependence. We demonstrate analytically and by means of a series of simulation experiments how evidence of the removal of spatial autocorrelation by spatial fixed effects may be spurious when the true data generating processes (DGP) takes the form of a spatial lag or spatial error dependence. In addition, we also show that spatial fixed effects correctly remove spatial correlation only in the special case where the dependence is group-wise, with all observations in the same group as neighbours of each other.

Original languageEnglish (US)
Pages (from-to)3-17
Number of pages15
JournalPapers in Regional Science
Volume92
Issue number1
DOIs
StatePublished - Mar 2013

Fingerprint

cross section
econometrics
autocorrelation
Group
inclusion
regression
simulation
experiment
evidence
effect
removal

Keywords

  • Spatial autocorrelation
  • Spatial econometrics
  • Spatial externalities
  • Spatial fixed effects
  • Spatial interaction
  • Spatial weights

ASJC Scopus subject areas

  • Environmental Science (miscellaneous)
  • Geography, Planning and Development

Cite this

Spatial fixed effects and spatial dependence in a single cross-section. / Anselin, Luc; Arribas-Bel, Daniel.

In: Papers in Regional Science, Vol. 92, No. 1, 03.2013, p. 3-17.

Research output: Contribution to journalArticle

Anselin, Luc ; Arribas-Bel, Daniel. / Spatial fixed effects and spatial dependence in a single cross-section. In: Papers in Regional Science. 2013 ; Vol. 92, No. 1. pp. 3-17.
@article{8f6edcde6365482eb35f7a5bcdb8e4cf,
title = "Spatial fixed effects and spatial dependence in a single cross-section",
abstract = "We investigate the common conjecture in applied econometric work that the inclusion of spatial fixed effects in a regression specification for a single cross-sectional data set removes spatial dependence. We demonstrate analytically and by means of a series of simulation experiments how evidence of the removal of spatial autocorrelation by spatial fixed effects may be spurious when the true data generating processes (DGP) takes the form of a spatial lag or spatial error dependence. In addition, we also show that spatial fixed effects correctly remove spatial correlation only in the special case where the dependence is group-wise, with all observations in the same group as neighbours of each other.",
keywords = "Spatial autocorrelation, Spatial econometrics, Spatial externalities, Spatial fixed effects, Spatial interaction, Spatial weights",
author = "Luc Anselin and Daniel Arribas-Bel",
year = "2013",
month = "3",
doi = "10.1111/j.1435-5957.2012.00480.x",
language = "English (US)",
volume = "92",
pages = "3--17",
journal = "Papers in Regional Science",
issn = "1056-8190",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Spatial fixed effects and spatial dependence in a single cross-section

AU - Anselin, Luc

AU - Arribas-Bel, Daniel

PY - 2013/3

Y1 - 2013/3

N2 - We investigate the common conjecture in applied econometric work that the inclusion of spatial fixed effects in a regression specification for a single cross-sectional data set removes spatial dependence. We demonstrate analytically and by means of a series of simulation experiments how evidence of the removal of spatial autocorrelation by spatial fixed effects may be spurious when the true data generating processes (DGP) takes the form of a spatial lag or spatial error dependence. In addition, we also show that spatial fixed effects correctly remove spatial correlation only in the special case where the dependence is group-wise, with all observations in the same group as neighbours of each other.

AB - We investigate the common conjecture in applied econometric work that the inclusion of spatial fixed effects in a regression specification for a single cross-sectional data set removes spatial dependence. We demonstrate analytically and by means of a series of simulation experiments how evidence of the removal of spatial autocorrelation by spatial fixed effects may be spurious when the true data generating processes (DGP) takes the form of a spatial lag or spatial error dependence. In addition, we also show that spatial fixed effects correctly remove spatial correlation only in the special case where the dependence is group-wise, with all observations in the same group as neighbours of each other.

KW - Spatial autocorrelation

KW - Spatial econometrics

KW - Spatial externalities

KW - Spatial fixed effects

KW - Spatial interaction

KW - Spatial weights

UR - http://www.scopus.com/inward/record.url?scp=84874575232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874575232&partnerID=8YFLogxK

U2 - 10.1111/j.1435-5957.2012.00480.x

DO - 10.1111/j.1435-5957.2012.00480.x

M3 - Article

VL - 92

SP - 3

EP - 17

JO - Papers in Regional Science

JF - Papers in Regional Science

SN - 1056-8190

IS - 1

ER -