Two techniques for exploring non-stationarity in geographical data

Stewart Fotheringham, Martin Charlton, Christopher Brunsdon

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

This paper is concerned with the exploratory analysis of non-stationarity, the variation in parameter estimates across data sets, in spatial data. Two modelling paradigms are demonstrated in which local variation in the structure of a model is considered rather than the fitting of a global model to a set of spatial data. Using data for an area in North East Scotland, we first demonstrate some problems of non-stationarity in a multiple regression model using a moving window to fit a large number of local models within the study area, the results of the modelling being visualised in a GIS environment. In particular we examine the localised variation in the model coefficients and goodness of fit. The second technique consists of a more formal modelling framework in which spatial non-stationarity can be both measured and modelled. This technique is known as Geographically Weighted Regression (GWR) and an empirical example of the technique is described using data on the relationship between health and socio-economic data in the city of Newcastle in Northeast England.

Original languageEnglish (US)
Pages (from-to)59-82
Number of pages24
JournalGeographical Systems
Volume4
Issue number1
StatePublished - 1997
Externally publishedYes

Fingerprint

spatial data
modeling
multiple regression
regression
GIS
Geographical Information System
paradigm
health
economics
global model
analysis
economic data
city
socioeconomics
parameter

Keywords

  • Exploratory spatial data analysis
  • Geographically Weighted Regression
  • Moving window
  • Spatial non-stationarity
  • Visualisation

ASJC Scopus subject areas

  • Earth and Planetary Sciences (miscellaneous)

Cite this

Two techniques for exploring non-stationarity in geographical data. / Fotheringham, Stewart; Charlton, Martin; Brunsdon, Christopher.

In: Geographical Systems, Vol. 4, No. 1, 1997, p. 59-82.

Research output: Contribution to journalArticle

Fotheringham, Stewart ; Charlton, Martin ; Brunsdon, Christopher. / Two techniques for exploring non-stationarity in geographical data. In: Geographical Systems. 1997 ; Vol. 4, No. 1. pp. 59-82.
@article{ea6d847e1d844d4a9830ecd161179740,
title = "Two techniques for exploring non-stationarity in geographical data",
abstract = "This paper is concerned with the exploratory analysis of non-stationarity, the variation in parameter estimates across data sets, in spatial data. Two modelling paradigms are demonstrated in which local variation in the structure of a model is considered rather than the fitting of a global model to a set of spatial data. Using data for an area in North East Scotland, we first demonstrate some problems of non-stationarity in a multiple regression model using a moving window to fit a large number of local models within the study area, the results of the modelling being visualised in a GIS environment. In particular we examine the localised variation in the model coefficients and goodness of fit. The second technique consists of a more formal modelling framework in which spatial non-stationarity can be both measured and modelled. This technique is known as Geographically Weighted Regression (GWR) and an empirical example of the technique is described using data on the relationship between health and socio-economic data in the city of Newcastle in Northeast England.",
keywords = "Exploratory spatial data analysis, Geographically Weighted Regression, Moving window, Spatial non-stationarity, Visualisation",
author = "Stewart Fotheringham and Martin Charlton and Christopher Brunsdon",
year = "1997",
language = "English (US)",
volume = "4",
pages = "59--82",
journal = "Journal of Geographical Systems",
issn = "1435-5930",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Two techniques for exploring non-stationarity in geographical data

AU - Fotheringham, Stewart

AU - Charlton, Martin

AU - Brunsdon, Christopher

PY - 1997

Y1 - 1997

N2 - This paper is concerned with the exploratory analysis of non-stationarity, the variation in parameter estimates across data sets, in spatial data. Two modelling paradigms are demonstrated in which local variation in the structure of a model is considered rather than the fitting of a global model to a set of spatial data. Using data for an area in North East Scotland, we first demonstrate some problems of non-stationarity in a multiple regression model using a moving window to fit a large number of local models within the study area, the results of the modelling being visualised in a GIS environment. In particular we examine the localised variation in the model coefficients and goodness of fit. The second technique consists of a more formal modelling framework in which spatial non-stationarity can be both measured and modelled. This technique is known as Geographically Weighted Regression (GWR) and an empirical example of the technique is described using data on the relationship between health and socio-economic data in the city of Newcastle in Northeast England.

AB - This paper is concerned with the exploratory analysis of non-stationarity, the variation in parameter estimates across data sets, in spatial data. Two modelling paradigms are demonstrated in which local variation in the structure of a model is considered rather than the fitting of a global model to a set of spatial data. Using data for an area in North East Scotland, we first demonstrate some problems of non-stationarity in a multiple regression model using a moving window to fit a large number of local models within the study area, the results of the modelling being visualised in a GIS environment. In particular we examine the localised variation in the model coefficients and goodness of fit. The second technique consists of a more formal modelling framework in which spatial non-stationarity can be both measured and modelled. This technique is known as Geographically Weighted Regression (GWR) and an empirical example of the technique is described using data on the relationship between health and socio-economic data in the city of Newcastle in Northeast England.

KW - Exploratory spatial data analysis

KW - Geographically Weighted Regression

KW - Moving window

KW - Spatial non-stationarity

KW - Visualisation

UR - http://www.scopus.com/inward/record.url?scp=0001952078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001952078&partnerID=8YFLogxK

M3 - Article

VL - 4

SP - 59

EP - 82

JO - Journal of Geographical Systems

JF - Journal of Geographical Systems

SN - 1435-5930

IS - 1

ER -