Non-Stationary Semivariogram Analysis Using Real Estate Transaction Data

Piyawan Srikhum and Arnaud Simon ()
Additional contact information
Arnaud Simon: DRM - Dauphine Recherches en Management - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique

Post-Print from HAL

Abstract: Geostatistical model is one of spatial statistical methodologies used for correcting spatial autocorrelation problem. To apply this model, two common assumptions should be made to allow global homogeneity: spatial continuity and spatial stationary. In different fields of research such as geography, environmental science and computer science, they usually take into account a violation of the second assumption (spatial stationary) but no article works under non-stationary condition in real estate research fields. This article is probably a first attempt to examine the violation of stationary assumption, in term of time and space, using transaction prices, from 1998 to 2007, of Parisian properties situated 5 kilometers around Arc de Triomphe. By comparing estimated 1-year semivariogram to 10-years semivariogram function, we found evidence of non-time-stationary. Likewise, non-spatial-stationary problem was detected by segmenting data in 90 degrees rotating windows. Our results show that we should not compute a common variogram for all parts of the region of interest.

Keywords: non-stationary; spatial autocorrelation; geostatistical model (search for similar items in EconPapers)
Date: 2010-06-24
References: Add references at CitEc
Citations:

Published in ERES 2010, Jun 2010, Milan, Italy

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:halshs-00551308

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().