The function subsets a spatial weights list, retaining objects for which the subset argument vector is TRUE. At present it will only subset non-general weights lists (that is those created by nb2listw with glist=NULL).

# S3 method for listw
subset(x, subset, zero.policy = NULL, ...)

Arguments

x

an object of class listw

subset

logical expression

zero.policy

default NULL, use global option value; if FALSE stop with error for any empty neighbour sets, if TRUE permit the weights list to be formed with zero-length weights vectors - passed through to nb2listw

...

generic function pass-through

Value

The function returns an object of class listw with component style the same as the input object, component neighbours a list of integer vectors containing neighbour region number ids (compacted to run from 1:number of regions in subset), and component weights as the weights computed for neighbours using style.

Author

Roger Bivand Roger.Bivand@nhh.no

See also

Examples

col.gal.nb <- read.gal(system.file("weights/columbus.gal", package="spData")[1])
to.be.dropped <- c(31, 34, 36, 39, 42, 46)
pre <- nb2listw(col.gal.nb)
print(pre)
#> Characteristics of weights list object:
#> Neighbour list object:
#> Number of regions: 49 
#> Number of nonzero links: 230 
#> Percentage nonzero weights: 9.579342 
#> Average number of links: 4.693878 
#> 
#> Weights style: W 
#> Weights constants summary:
#>    n   nn S0       S1       S2
#> W 49 2401 49 23.48489 204.6687
post <- subset(pre, !(1:length(col.gal.nb) %in% to.be.dropped))
print(post)
#> Characteristics of weights list object:
#> Neighbour list object:
#> Number of regions: 43 
#> Number of nonzero links: 212 
#> Percentage nonzero weights: 11.46566 
#> Average number of links: 4.930233 
#> 
#> Weights style: W 
#> Weights constants summary:
#>    n   nn S0       S1       S2
#> W 43 1849 43 19.26584 178.4604