1,309
Views
32
CrossRef citations to date
0
Altmetric
Articles

Local Spatiotemporal Modeling of House Prices: A Mixed Model Approach

Pages 189-201
Received 01 Jun 2014
Accepted 01 Sep 2014
Published online: 08 Jun 2015
 

The real estate market has long provided an active application area for spatial–temporal modeling and analysis and it is well known that house prices tend to be not only spatially but also temporally correlated. In the spatial dimension, nearby properties tend to have similar values because they share similar characteristics, but house prices tend to vary over space due to differences in these characteristics. In the temporal dimension, current house prices tend to be based on property values from previous years and in the spatial–temporal dimension, the properties on which current prices are based tend to be in close spatial proximity. To date, however, most research on house prices has adopted either a spatial perspective or a temporal one; relatively little effort has been devoted to situations where both spatial and temporal effects coexist. Using ten years of house price data in Fife, Scotland (2003–2012), this research applies a mixed model approach, semiparametric geographically weighted regression (GWR), to explore, model, and analyze the spatiotemporal variations in the relationships between house prices and associated determinants. The study demonstrates that the mixed modeling technique provides better results than standard approaches to predicting house prices by accounting for spatiotemporal relationships at both global and local scales.

长久以来,不动产市场为空间时间模式化及分析,提供了有效的应用范围;而房屋价格不仅倾向与空间相关,亦与时间相关,则是众所皆知的事。在空间面向上,相互比邻的不动产,因为具有类似的特徵,而倾向拥有相似的价值,但房屋价格则因特徵的差异,在空间上倾向彼此不同。在时间面向上,当前的房屋价格,倾向根据历年来的不动产价值;而在空间—时间面向上,作为当前价格基础的不动产,则倾向具有空间邻近性。但至今的住宅价格研究,多半仅採取空间或时间的视角;相对而言,显少有研究投注于空间及时间效应共存的状态。本研究运用苏格兰法夫中,十年(2003–2012)的房市价格数据,应用混合模型方法——半参数地理加权迴归(GWR)——来探讨、模式化并分析房屋价格与相关决定因素之间的关係之空间时间变异。本研究证实,混合模型技术,透过考量全球与在地尺度的空间时间关係,因此相较于标准方法而言,在预测房屋价格上能获得更佳的结果。

Desde hace mucho tiempo el mercado de bienes raíces ha sido una activa área de aplicación del modelado y análisis espacial-temporal, y es bien sabido que los precios de los inmuebles tienden a estar correlacionados no solo espacial sino temporalmente. En la dimensión espacial, las propiedades próximas tienden a tener valores similares porque comparten características similares, pero el precio de las casas tiende a variar a través del espacio debido a diferencias en tales características. En la dimensión temporal, los precios actuales de las casas tienden a basarse en los valores de la propiedad en años anteriores, y en la dimensión espacial-temporal, las propiedades en las que se basan los precios actuales tienden a estar en una cercana proximidad espacial. Hasta el momento, sin embargo, la mayor parte de la investigación sobre precios de la vivienda ha adoptado, o una perspectiva espacial, o una temporal; relativamente muy poco esfuerzo se le ha dedicado a situaciones donde coexistan los efectos espaciales y temporales. Utilizando datos de precios de las casas en diez años en Fife, Escocia (2003–2012), esta investigación aplica un modelo de aproximación mixta, la regresión geográficamente ponderada semiparamétrica (GWR), para explorar, modelar y analizar las variaciones espaciotemporales en las relaciones entre precios de las casas y los determinantes asociados. El estudio demuestra que la técnica de modelado mixta da mejores resultados que los enfoques estándar de predicción de precios de los inmuebles, al tomar en cuenta las relaciones espaciotemporales, tanto a escalas globales como locales.

Notes

1 We use N = 1,000 because of the computational complexity. We also run the MC test with N = 100, which gave similar results as those from N = 1,000, which indicates that the MC test is rigorous.

Additional information

Notes on contributors

Jing Yao

JING YAO is a Lecturer at the Urban Big Data Centre in the School of Social and Political Sciences at University of Glasgow, Glasgow, UK G12 8RZ. E-mail: Jing.Yao@glasgow.ac.uk. Her research interests include but not are limited to GIScience, spatial statistics, health geography, location modeling and spatial optimization, and urban and regional planning.

A. Stewart Fotheringham

A. STEWART FOTHERINGHAM is a Professor at GeoDa Centre for Geospatial Analysis and Computation, School of Geographical Sciences and Urban Planning, Arizona State University, Tempe, AZ 85281. E-mail: Stewart.Fotheringham@asu.edu. His research interests include but are not limited to GIScience, spatial statistics, spatial interaction modeling, health geography, transportation, migration analysis, house price analysis, retail geography, and crime pattern analysis.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
GBP 37.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
GBP 119.00 Add to cart

* Local tax will be added as applicable
 

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.