Eres : Digital Library : Works

Paper eres2009_153:
Predicting House Prices with Spatial Dependence: A Comparison of Alternative Methods

id eres2009_153
authors Hoesli, Martin; Bourassa, Steven; Cantoni, Eva
year 2009
title Predicting House Prices with Spatial Dependence: A Comparison of Alternative Methods
source 16th Annual European Real Estate Society Conference in Stockholm, Sweden
summary This paper compares alternative methods for taking spatial dependence into account in house price prediction. We select hedonic methods that have been reported in the literature to perform relatively well in terms of ex-sample prediction accuracy. Because differences in performance may be due to differences in data, we compare the methods using a single data set. The estimation methods include simple OLS, a two-stage process incorporating nearest neighbors’ residuals in the second stage, geostatistical, and trend surface models. These models take into account submarkets by adding dummy variables or by estimating separate equations for each submarket. Submarkets are defined at different levels of aggregation. We conclude that a geostatistical model with disaggregated submarket variables performs best.
series ERES:conference
email martin.hoesli@unige.ch, steven.bourassa@louisville.edu, eva.cantoni@unige.ch
content file.ppt (410,112 bytes)
discussion No discussions. Post discussion ...
ratings
session Housing
last changed 2009/09/16 16:22
HOMELOGIN (you are user _anon_519807 from group guest) Powered by SciX Open Publishing Services 1.002