ggwr: Generalised geographically weighted regression

Description

The function implements generalised geographically weighted regression approach to exploring spatial non-stationarity for given global bandwidth and chosen weighting scheme.

Usage

ggwr(formula, data = list(), coords, bandwidth, gweight = gwr.Gauss,
 adapt = NULL, fit.points, family = gaussian, longlat = NULL, type = 
c("working", "deviance", "pearson", "response"))

Value

A list of class “gwr”:

SDF: a SpatialPointsDataFrame (may be gridded) or SpatialPolygonsDataFrame object (see package "sp") with fit.points, weights, GWR coefficient estimates, dispersion if a "quasi"-family is used, and the residuals of type "type" in its "data" slot.
lhat: Leung et al. L matrix, here set to NA
lm: GLM global regression on the same model formula.
bandwidth: the bandwidth used.
this.call: the function call used.

Arguments

formula: regression model formula as in glm
data: model data frame as in glm, or may be a SpatialPointsDataFrame or SpatialPolygonsDataFrame object as defined in package sp
coords: matrix of coordinates of points representing the spatial positions of the observations
bandwidth: bandwidth used in the weighting function, possibly calculated by ggwr.sel
gweight: geographical weighting function, at present gwr.Gauss() default, or gwr.gauss(), the previous default or gwr.bisquare()
adapt: either NULL (default) or a proportion between 0 and 1 of observations to include in weighting scheme (k-nearest neighbours)
fit.points: an object containing the coordinates of fit points; often an object from package sp; if missing, the coordinates given through the data argument object, or the coords argument are used
family: a description of the error distribution and link function to be used in the model, see glm
longlat: TRUE if point coordinates are longitude-latitude decimal degrees, in which case distances are measured in kilometers; if x is a SpatialPoints object, the value is taken from the object itself
type: the type of residuals which should be returned. The alternatives are: "working" (default), "pearson", "deviance" and "response"

Author

Roger Bivand Roger.Bivand@nhh.no

References

Fotheringham, A.S., Brunsdon, C., and Charlton, M.E., 2002, Geographically Weighted Regression, Chichester: Wiley; http://gwr.nuim.ie/

Examples

Run this code

if (require(sf)) {
xx <- as(st_read(system.file("shapes/sids.gpkg", package="spData")[1]), "Spatial")
bw <- 144.4813
if (FALSE) {
bw <- ggwr.sel(SID74 ~ I(NWBIR74/BIR74) + offset(log(BIR74)), data=xx,
  family=poisson(), longlat=TRUE)
}
nc <- ggwr(SID74 ~ I(NWBIR74/BIR74) + offset(log(BIR74)), data=xx,
  family=poisson(), longlat=TRUE, bandwidth=bw)
nc
if (FALSE) {
nc <- ggwr(SID74 ~ I(NWBIR74/10000) + offset(log(BIR74)), data=xx,
  family=poisson(), longlat=TRUE, bandwidth=bw)
nc
nc <- ggwr(SID74 ~ I(NWBIR74/10000) + offset(log(BIR74)), data=xx,
  family=quasipoisson(), longlat=TRUE, bandwidth=bw)
nc
}
}

Run the code above in your browser using DataLab

State of Data and AI Literacy Report 2025