Compute Geary's C
A simple function to compute Geary's C, called by geary.test and geary.mc;
C = \frac{(n-1)}{2∑_{i=1}^{n}∑_{j=1}^{n}w_{ij}} \frac{∑_{i=1}^{n}∑_{j=1}^{n}w_{ij}(x_i-x_j)^2}{∑_{i=1}^{n}(x_i - \bar{x})^2}
geary.intern is an internal function used to vary the similarity
criterion.
geary(x, listw, n, n1, S0, zero.policy=NULL)
x |
a numeric vector the same length as the neighbours list in listw |
listw |
a |
n |
number of zones |
n1 |
n - 1 |
S0 |
global sum of weights |
zero.policy |
default NULL, use global option value; if TRUE assign zero to the lagged value of zones without neighbours, if FALSE assign NA |
a list with
C |
Geary's C |
K |
sample kurtosis of x |
Roger Bivand Roger.Bivand@nhh.no
Cliff, A. D., Ord, J. K. 1981 Spatial processes, Pion, p. 17.
data(oldcol) col.W <- nb2listw(COL.nb, style="W") str(geary(COL.OLD$CRIME, col.W, length(COL.nb), length(COL.nb)-1, Szero(col.W)))
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.