umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Predicting Housing Prices with GIS: Universal kriging in Jämtland County
Umeå University, Faculty of Social Sciences, Department of Geography and Economic History, Economic and social geography.
2018 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Location is a key-component in real estate and the northern Swedish county of Jä-mtland makes no exception. While certain municipalities experience-growing ac-tive markets, other display a stagnating situation. Nevertheless, within the vast mu-nicipalities of Jämtland, it is possible to expect large variations among property prices due to different geographical settings determined by population densities, infrastructures, job markets and natural amenities. Thus statistics aggregated on a County or municipal level do not display an accurate picture of local housing mar-kets and accurate insights on local price variations might be beneficial for a wide array of actors. Accordingly, this thesis aims to develop a model predicting infor-mation for residential property values on a micro-geographical scale for the Jämt-land county. The model should identify residential property values (SEK/m²) and determine the accuracy of the prediction. Spatial interpolation is chosen among dif-ferent realms available in GIS to fulfil the aim of the study. Spatial interpolation allows the production of price-prediction map for house prices at unsampled loca-tions starting from a delimited amount of recorded transactions. In particular, the geostatistical technique of universal kriging is chosen since it allows to measure the efficiency of the prediction and it is particularly suited for the case, due to the ex-pected strong spatial dependence of house prices in Jämtland. The analysis carried out in ArcGIS delivers reliable results. On a micro-geographical level, the county shows similar local housing markets, such as those in the mountain touristic local-ities or in the sparsely populated rural areas. The Scandinavian Mountains have a strong driving effect on real estate; touristic localities such as Vemdalen, Funäsda-len and Åre display the highest prices in Jämtland, in the range of more than 45000 SEK/m². On the contrary most of the sparsely populated and rural areas in eastern Jämtland, unless located within municipal centres (e.g., Sveg or Strömsund), dis-play extremely low prices, in the range of less than 4000 SEK/m². The regional centrum of Östersund shows higher prices than the regional average. Nevertheless, the city’s price range is lower than in many touristic localities and there are no ma-jor differences between different areas of the city. Östersund creates a catalytic ef-fect for the nearby countryside, which displays substantially higher prices than other rural areas. Universal kriging is a suitable technique to map price variation, even in vast regions, such as Jämtland County. Nevertheless, the accuracy of the prediction strongly relies on the analyst’s modelling skills and on the adequate dis-tribution of observations. Furthermore, spatial patterns are not sufficient to en-tirely analyse price variation in more competitive and complex markets, such as in touristic centres and in Östersund, where other issues might be at stake.

Place, publisher, year, edition, pages
2018. , p. 52
Keywords [en]
interpolation, universal kriging, housing prices, real estate, Sweden
National Category
Human Geography
Identifiers
URN: urn:nbn:se:umu:diva-148796OAI: oai:DiVA.org:umu-148796DiVA, id: diva2:1216489
Subject / course
Examensarbete i Geografi, för magisterexamen
Supervisors
Examiners
Available from: 2018-06-12 Created: 2018-06-11 Last updated: 2018-06-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Economic and social geography
Human Geography

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 79 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf