USCounties {Matrix}R Documentation

USCounties Contiguity Matrix


This matrix represents the contiguities of 3111 US counties using the Queen criterion of at least a single shared boundary point. The representation is as a row standardised spatial weights matrix transformed to a symmetric matrix (see Ord (1975), p. 125).




A 3111 ^2 symmetric sparse matrix of class dsCMatrix with 9101 non-zero entries.


The data were read into R using, and row-standardised and transformed to symmetry using nb2listw and similar.listw. This spatial weights object was converted to class dsCMatrix using as_dsTMatrix_listw and coercion.


The data were retrieved from, files “usc.txt” and “usc\_q.GAL”, with permission for use and distribution from Luc Anselin (in early 2008).


Ord, J. K. (1975) Estimation methods for models of spatial interaction; Journal of the American Statistical Association 70, 120–126.


(n <- ncol(USCounties))
IM <- .symDiagonal(n)
nn <- 50
rho <- runif(nn, 0, 1)
system.time(MJ <- sapply(rho, function(x)
	determinant(IM - x * USCounties, logarithm = TRUE)$modulus))

## can be done faster, by update()ing the Cholesky factor:
nWC <- -USCounties
C1 <- Cholesky(nWC, Imult = 2)
system.time(MJ1 <- n * log(rho) +
            sapply(rho, function(x)
                   2 * c(determinant(update(C1, nWC, 1/x))$modulus)))
all.equal(MJ, MJ1)

C2 <- Cholesky(nWC, super = TRUE, Imult = 2)
system.time(MJ2 <- n * log(rho) +
            sapply(rho, function(x)
                   2 * c(determinant(update(C2, nWC, 1/x))$modulus)))
all.equal(MJ, MJ2)  
system.time(MJ3 <- n * log(rho) + Matrix:::ldetL2up(C1, nWC, 1/rho))
stopifnot(all.equal(MJ, MJ3))
system.time(MJ4 <- n * log(rho) + Matrix:::ldetL2up(C2, nWC, 1/rho))
stopifnot(all.equal(MJ, MJ4))

[Package Matrix version 1.4-1 Index]