GWR Gaussian weights function
The gwr.gauss function returns a vector of weights using the Gaussian scheme:
w(g) = e^{{-(d/h)}^2}
where d are the distances between the observations and h is the bandwidth.
The default (from release 0.5) gwr.Gauss function returns a vector of weights using the Gaussian scheme:
w(g) = e^{-(1/2) {{(d/h)}^2}}
gwr.gauss(dist2, bandwidth) gwr.Gauss(dist2, bandwidth)
dist2 |
vector of squared distances between observations and fit point |
bandwidth |
bandwidth |
vector of weights.
Roger Bivand Roger.Bivand@nhh.no
Fotheringham, A.S., Brunsdon, C., and Charlton, M.E., 2000, Quantitative Geography, London: Sage; C. Brunsdon, A.Stewart Fotheringham and M.E. Charlton, 1996, "Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity", Geographical Analysis, 28(4), 281-298; http://gwr.nuim.ie/
plot(seq(-10,10,0.1), gwr.Gauss(seq(-10,10,0.1)^2, 3.5), type="l")
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.