Spatial Dependence, Housing Submarkets, and House Price Prediction

Steven C. Bourassa, Eva Cantoni, Martin Edward Ralph Hoesli

Research output: Contribution to journalArticle

97 Citations (Scopus)

Abstract

This paper compares alternative methods of controlling for the spatial dependence of house prices in a mass appraisal context. Explicit modeling of the error structure is characterized as a relatively fluid approach to defining housing submarkets. This approach allows the relevant submarket to vary from house to house and for transactions involving other dwellings in each submarket to have varying impacts depending on distance. We conclude that—for our Auckland, New Zealand, data—the gains in accuracy from including submarket variables in an ordinary least squares specification are greater than any benefits from using geostatistical or lattice methods. This conclusion is of practical importance, as a hedonic model with submarket dummy variables is substantially easier to implement than spatial statistical methods.
Original languageEnglish
Pages (from-to)143-160
Number of pages18
JournalThe Journal of Real Estate Finance and Economics
Volume35
Issue number2
Early online date2 Jun 2007
DOIs
Publication statusPublished - Aug 2007

Fingerprint

housing
prediction
statistical method
transaction
New Zealand
fluid
modeling
price
method
Prediction
House prices
Spatial dependence
Housing prices
Hedonic model
Statistical methods
Ordinary least squares
Modeling
Dummy variables
appraisal
dwelling

Keywords

  • spatial dependence
  • hedonic price models
  • geostatistical models
  • lattice models
  • mass appraisal
  • housing submarkets

Cite this

Spatial Dependence, Housing Submarkets, and House Price Prediction. / Bourassa, Steven C.; Cantoni, Eva; Hoesli, Martin Edward Ralph.

In: The Journal of Real Estate Finance and Economics, Vol. 35, No. 2, 08.2007, p. 143-160.

Research output: Contribution to journalArticle

@article{0f6ee6a578f54c3da0925856a52ec69a,
title = "Spatial Dependence, Housing Submarkets, and House Price Prediction",
abstract = "This paper compares alternative methods of controlling for the spatial dependence of house prices in a mass appraisal context. Explicit modeling of the error structure is characterized as a relatively fluid approach to defining housing submarkets. This approach allows the relevant submarket to vary from house to house and for transactions involving other dwellings in each submarket to have varying impacts depending on distance. We conclude that—for our Auckland, New Zealand, data—the gains in accuracy from including submarket variables in an ordinary least squares specification are greater than any benefits from using geostatistical or lattice methods. This conclusion is of practical importance, as a hedonic model with submarket dummy variables is substantially easier to implement than spatial statistical methods.",
keywords = "spatial dependence, hedonic price models, geostatistical models, lattice models, mass appraisal, housing submarkets",
author = "Bourassa, {Steven C.} and Eva Cantoni and Hoesli, {Martin Edward Ralph}",
year = "2007",
month = "8",
doi = "10.1007/s11146-007-9036-8",
language = "English",
volume = "35",
pages = "143--160",
journal = "The Journal of Real Estate Finance and Economics",
issn = "0895-5638",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Spatial Dependence, Housing Submarkets, and House Price Prediction

AU - Bourassa, Steven C.

AU - Cantoni, Eva

AU - Hoesli, Martin Edward Ralph

PY - 2007/8

Y1 - 2007/8

N2 - This paper compares alternative methods of controlling for the spatial dependence of house prices in a mass appraisal context. Explicit modeling of the error structure is characterized as a relatively fluid approach to defining housing submarkets. This approach allows the relevant submarket to vary from house to house and for transactions involving other dwellings in each submarket to have varying impacts depending on distance. We conclude that—for our Auckland, New Zealand, data—the gains in accuracy from including submarket variables in an ordinary least squares specification are greater than any benefits from using geostatistical or lattice methods. This conclusion is of practical importance, as a hedonic model with submarket dummy variables is substantially easier to implement than spatial statistical methods.

AB - This paper compares alternative methods of controlling for the spatial dependence of house prices in a mass appraisal context. Explicit modeling of the error structure is characterized as a relatively fluid approach to defining housing submarkets. This approach allows the relevant submarket to vary from house to house and for transactions involving other dwellings in each submarket to have varying impacts depending on distance. We conclude that—for our Auckland, New Zealand, data—the gains in accuracy from including submarket variables in an ordinary least squares specification are greater than any benefits from using geostatistical or lattice methods. This conclusion is of practical importance, as a hedonic model with submarket dummy variables is substantially easier to implement than spatial statistical methods.

KW - spatial dependence

KW - hedonic price models

KW - geostatistical models

KW - lattice models

KW - mass appraisal

KW - housing submarkets

U2 - 10.1007/s11146-007-9036-8

DO - 10.1007/s11146-007-9036-8

M3 - Article

VL - 35

SP - 143

EP - 160

JO - The Journal of Real Estate Finance and Economics

JF - The Journal of Real Estate Finance and Economics

SN - 0895-5638

IS - 2

ER -