The modelling of housing submarkets
| Pages | 473-487 |
| Published date | 01 August 2000 |
| Date | 01 August 2000 |
| DOI | https://doi.org/10.1108/14635780010345436 |
| Author | Mike Fletcher,Paul Gallimore,Jean Mangan |
| Subject Matter | Property management & built environment |
Academic papers:
Housing
submarkets
473
Journal of Property Investment &
Finance, Vol. 18 No. 4, 2000,
pp. 473-487. #MCB University
Press, 1463-578X
Received 20 April 1999
Revised 8 February 2000
ACADEMIC PAPERS
The modelling of housing
submarkets
Mike Fletcher
School of Computing, Staffordshire University, Stoke-on-Trent, UK
Paul Gallimore
Department of Surveying, Nottingham Trent University,
Nottingham, UK, and
Jean Mangan
Business School, Staffordshire University, Stoke-on-Trent, UK
Keywords Housing markets, Forecasting, Modelling
Abstract This paper is concerned as to whether it is more appropriate to use aggregate or
disaggregate models in forecasting house prices using hedonic modelling. It is accepted that the
implicit pricing of some of the attributes is not stable between locations, property types and ages
but it is argued that this can be effectively modelled with an aggregate method. The models are
developed using a dataset of nearly 18,000 transactions in the UK Midlands region in 1994. The
comparative performance of these models is then considered using two approaches. Chow tests of
the error differences between actual price and the price predicted by the models suggest that the
submarket models lead to statistically significant, though small, improvements. A second
approach, using comparison of the root mean square errors, is conducted on the models'
forecasts for a 10 per cent sample of nearly 2,000 transactions excluded from the modelling
process. This shows little practical difference in the forecasting ability between the two approaches.
Great care needs to be taken over sample size if a disaggregate model is used.
Introduction
House prices embody the market's valuation of the array of characteristics
possessed by individual properties. In utilising information on house prices,
valuers seek comparable market transactions with minimal differences in
characteristics between the property being valued and market sales. Single-
property valuation, therefore, is less concerned with explicit consideration of
the values ascribable to characteristics than with their gross effect and
adjustments for minor differences. It is by nature reliant upon a small number
of transactions. By contrast, hedonic modelling of house prices is concerned
with estimating the market's implicit pricing of each property characteristic.
This is done by regressing the transaction prices of properties against
corresponding property characteristics (or more precisely, against
measurements that reflect the presence or amount of each of these
characteristics). It is by nature reliant upon a large number of transactions.
While hedonic models can be used to estimate the value of individual
properties, they have tended to be used more often, in the UK at least, to explain
housing behaviour or to track house price changes at the national or regional
The research register for this journal is available at
http://www.mcbup.com/research_registers/jpif.asp
The current issue and full text archive of this journal is available at
http://www.emerald-library.com
To continue reading
Request your trial