Modelling Spatial Heterogeneity with Geographically Weighted Models (Introducing the new GWModel R package)

COURSE TUTOR: Martin Charlton, Chris Brunsdon and Paul Harris

DATE: 23rd – 24th April 2014

TIME: 10.00-17.00

LOCATION: Geographical Sciences

It is essential to register because places are limited. The registration form and details of how to register are here.


DESCRIPTION: Spatial statistics is a growing discipline providing important analytical techniques in a wide range of disciplines in the natural and social/economic sciences. In this workshop, we introduce techniques from a particular branch of spatial statistics, termed geographically weighted (GW) models.

GW models suit situations when data are not described well by some global model, but where there are spatial regions where a suitably localised calibration provides a better description. The approach uses a moving window weighting technique, where localised models are found at target locations. Commonly, outputs are mapped to provide a useful exploratory tool into the nature of the data’s spatial heterogeneity.

Key GW techniques include: GW summary statistics, GW boxplots, GW principal components analysis, GW regression, GW generalised linear models, GW discriminant analysis and GW variograms.

Of all the GW techniques, GW regression is the most popular and has been widely applied. This workshop now expands the GW model paradigm to other GW forms, providing hands-on exercises such that participants can apply the GW techniques themselves. Emphasis is firmly on applications rather than statistical theory.

The workshop requires personal work and interaction among the participants and instructors. Each component of the workshop will consist of a lecture followed by a computer practical using R, where real case studies in the natural and social/economic sciences will be used. The workshop programme will consist of the following four core components:

  1. Introductions - outline; GW modelling overview; R; GWmodel R package; case study data sets; bibliography and resources.
  2. Exploring data with GW summary statistics – for spatially exploring univariate and bivariate data.
  3. Exploring data with GW principal components analysis – for spatially exploring multivariate data.
  4. Exploring data with GW regression – basic and locally-compensated models for exploring regression relationships.

Prerequisites: Some knowledge of basic statistical concepts and techniques. Familiarity with the R statistical programming language is useful, but not essential.