spdep (version 0.1-10)

droplinks: Drop links in a neighbours list

Description

Drops links to and from or just to a region from a neighbours list. The example corresponds to Fingleton's Table 1, p. 6, for lattices 5 to 19.

Usage

droplinks(nb, drop, sym=TRUE)

Arguments

nb

a neighbours list object of class nb

drop

either a logical vector the length of nb, or a character vector of named regions corresponding to nb's region.id attribute, or an integer vector of region numbers

sym

TRUE for removal of both "row" and "column" links, FALSE for only "row" links

Value

• The function returns an object of class nb with a list of integer vectors containing neighbour region number ids.

References

B. Fingleton (1999) Spurious spatial regression: some Monte Carlo results with a spatial unit root and spatial cointegration, Journal of Regional Science 39, pp. 1--19.

See Also

is.symmetric.nb

Examples

rho <- c(0.2, 0.5, 0.95, 0.999, 1.0)
ns <- c(5, 7, 9, 11, 13, 15, 17, 19)
mns <- matrix(0, nrow=length(ns), ncol=length(rho))
rownames(mns) <- ns
colnames(mns) <- rho
mxs <- matrix(0, nrow=length(ns), ncol=length(rho))
rownames(mxs) <- ns
colnames(mxs) <- rho
for (i in 1:length(ns)) {
  nblist <- cell2nb(ns[i], ns[i])
  nbdropped <- droplinks(nblist, ((ns[i]*ns[i])+1)/2, sym=FALSE)
  listw <- nb2listw(nbdropped, style="W", zero.policy=TRUE)
  wmat <- listw2mat(listw)
  for (j in 1:length(rho)) {
    mat <- diag(ns[i]*ns[i]) - rho[j] * wmat
    res <- diag(solve(t(mat) %*% mat))
    mns[i,j] <- mean(res)
    mxs[i,j] <- max(res)
  }
}
print(mns)
print(mxs)