Incorporating spatial variation in housing attribute prices: A comparison of geographically weighted regression and the spatial expansion method

Christopher Bitter, Gordon F. Mulligan, Sandy Dall Erba

Research output: Contribution to journalArticle

127 Citations (Scopus)

Abstract

Hedonic house price models typically impose a constant price structure on housing characteristics throughout an entire market area. However, there is increasing evidence that the marginal prices of many important attributes vary over space, especially within large markets. In this paper, we compare two approaches to examine spatial heterogeneity in housing attribute prices within the Tucson, Arizona housing market: the spatial expansion method and geographically weighted regression (GWR). Our results provide strong evidence that the marginal price of key housing characteristics varies over space. GWR outperforms the spatial expansion method in terms of explanatory power and predictive accuracy.

Original languageEnglish (US)
Pages (from-to)7-27
Number of pages21
JournalJournal of Geographical Systems
Volume9
Issue number1
DOIs
StatePublished - Apr 2007

Fingerprint

spatial variation
housing
regression
market
housing market
evidence
comparison
attribute
method
price

Keywords

  • Expansionmethod
  • Geographically weighted regression
  • Hedonic model
  • Houseprice
  • Spatialheterogeneity

ASJC Scopus subject areas

  • Geography, Planning and Development

Cite this

Incorporating spatial variation in housing attribute prices : A comparison of geographically weighted regression and the spatial expansion method. / Bitter, Christopher; Mulligan, Gordon F.; Dall Erba, Sandy.

In: Journal of Geographical Systems, Vol. 9, No. 1, 04.2007, p. 7-27.

Research output: Contribution to journalArticle

@article{0123f63ad37a4617b54340f7c71bc279,
title = "Incorporating spatial variation in housing attribute prices: A comparison of geographically weighted regression and the spatial expansion method",
abstract = "Hedonic house price models typically impose a constant price structure on housing characteristics throughout an entire market area. However, there is increasing evidence that the marginal prices of many important attributes vary over space, especially within large markets. In this paper, we compare two approaches to examine spatial heterogeneity in housing attribute prices within the Tucson, Arizona housing market: the spatial expansion method and geographically weighted regression (GWR). Our results provide strong evidence that the marginal price of key housing characteristics varies over space. GWR outperforms the spatial expansion method in terms of explanatory power and predictive accuracy.",
keywords = "Expansionmethod, Geographically weighted regression, Hedonic model, Houseprice, Spatialheterogeneity",
author = "Christopher Bitter and Mulligan, {Gordon F.} and {Dall Erba}, Sandy",
year = "2007",
month = "4",
doi = "10.1007/s10109-006-0028-7",
language = "English (US)",
volume = "9",
pages = "7--27",
journal = "Journal of Geographical Systems",
issn = "1435-5930",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Incorporating spatial variation in housing attribute prices

T2 - A comparison of geographically weighted regression and the spatial expansion method

AU - Bitter, Christopher

AU - Mulligan, Gordon F.

AU - Dall Erba, Sandy

PY - 2007/4

Y1 - 2007/4

N2 - Hedonic house price models typically impose a constant price structure on housing characteristics throughout an entire market area. However, there is increasing evidence that the marginal prices of many important attributes vary over space, especially within large markets. In this paper, we compare two approaches to examine spatial heterogeneity in housing attribute prices within the Tucson, Arizona housing market: the spatial expansion method and geographically weighted regression (GWR). Our results provide strong evidence that the marginal price of key housing characteristics varies over space. GWR outperforms the spatial expansion method in terms of explanatory power and predictive accuracy.

AB - Hedonic house price models typically impose a constant price structure on housing characteristics throughout an entire market area. However, there is increasing evidence that the marginal prices of many important attributes vary over space, especially within large markets. In this paper, we compare two approaches to examine spatial heterogeneity in housing attribute prices within the Tucson, Arizona housing market: the spatial expansion method and geographically weighted regression (GWR). Our results provide strong evidence that the marginal price of key housing characteristics varies over space. GWR outperforms the spatial expansion method in terms of explanatory power and predictive accuracy.

KW - Expansionmethod

KW - Geographically weighted regression

KW - Hedonic model

KW - Houseprice

KW - Spatialheterogeneity

UR - http://www.scopus.com/inward/record.url?scp=33947097410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947097410&partnerID=8YFLogxK

U2 - 10.1007/s10109-006-0028-7

DO - 10.1007/s10109-006-0028-7

M3 - Article

AN - SCOPUS:33947097410

VL - 9

SP - 7

EP - 27

JO - Journal of Geographical Systems

JF - Journal of Geographical Systems

SN - 1435-5930

IS - 1

ER -