There is now a range of software for running GWR and carrying out GW modelling. GWR4 is a standalone Windows application. GWmodel is an R library of GW modelling functions which includes GW regression. There are GWR options in several packages, including ArcGIS, SpaceStat and SAM. There are also a number of other R packages including spgwr,and gwrr.
GWR4 can be downloaded from this site, but you must register to be able to do so. GWmodel, and the other R packages can be downloaded from CRAN. (http://cran.r-project.org/). Theer are links below to site for the other packages.
GWmodel provides R users with a range of Geographically Weighted data analysis approaches within a single package, these include descriptive statistics, correlation, regression, general linear models and principal components analysis. The regression models include various for data with Gaussian, logistic and Poisson structures, as well as ridge regression for dealing with correlated predictors. A new feature of this package is the provision of robust versions of each technique – these are resistant to the effects of outliers.
Locations for modelling can be either in a projected coordinate system, or specified using geographical coordinates. Distance metrics include Euclidean, taxicab (Manhattan) and Minkowski, as well as Great Circle distances for locations specified by latitude/longitude coordinates. Various automatic calibration methods are also provided, and there are some helpful model building tools available to help select from alternative predictors.
Example datasets are also provided, and they are used in the accompanying documentation in illustrations of the use of the various techniques.
The documentation, with a description of the various functions, can be accessed at http://cran.r-project.org/web/packages/GWmodel/GWmodel.pdf.
You can download of a copy of the pre-print on GWmodel from http://arxiv.org/abs/1306.0413
Software for GWR for fitting Poisson, Logistic and Gaussian models, GWR3x, with a Visual Basic interface, used to be available from the NCG. This software is no longer supported, and its continued use is not recommended.
There are two R packages for running GWR:
spgwr provides a range of methods for estimating gwr models; authored by Roger Bivand and Danlin Yu.
gwrr provides additional tools for diagnosing collinearity in GWR models; authoried by David Wheeler
There are also implementations of GWR in other applications software:
ArcGIS: the Spatial Statistics toolbox, part of the core functionality of ArcMap provides a GWR tool for fitting Gaussian gwr models (http://resources.arcgis.com/en/help/main/10.1/index.html#/An_overview_of_the_Modeling_Spatial_Relationships_toolset/005p0000001w000000/)
SpaceStat, developed by Biomedware, allows GWR models to be fitted in a Windows environment (http://www.biomedware.com/?module=Page&sID=spacestat)
SAM – the Spatial Analysis in Macroecology package has an implementation of GWR (http://www.ecoevol.ufg.br/sam/)
We no longer recommend the use of GWR2.x.