[R-sig-Geo] FW: Including Alaska and Hawaii in listw Specifications of US States and Substate Regions

[Roger Bivand]

On Wed, 17 Jul 2019, Stuart Reece wrote:

> Hi,
>
> I was wanting to include a listw list of neighbours for USA states which
> include Alaska and Hawaii with Alaska a neighbour for Washington and Oregon
> states and Hawaii a neighbour for California and the Western continental US
> states.
>
> Naturally queen relationships fail.
>
> The Albers shapefiles at this URL are really useful for general mapping
> purposes but result in erroneous relationships with k-nearest neighbours
> when this is performed in GeoDa.
>
>
>
> These maps have Hawaii and Alaska elided to south of Texas.
>
>
>
> <https://github.com/hrbrmstr/albersusa>
> https://github.com/hrbrmstr/albersusa
>
>

They are troublesome to install, accessing just the file is impossible.

Did you look at the documentation of spdep::edit.nb()? Reading the list of 
functions and methods in a package tends to be helpful. Use 
spdep::make.sym.nb() after storing the output of edit.nb(). Because 
edit.nb() is interactive, I can't provide a script. The next release of 
spdep will support displaying sf polygons, for now you'd need to use:

usa <- usa_sf("aeqd")
nb <- spdep::poly2nb(usa)
crds <- st_coordinates(st_centroid(usa, of_largest_polygon=TRUE))
nb1 <- spdep::edit.nb(nb, crds, as(usa, "Spatial"))
nb2 <- spdep::make.sym.nb(nb1)

or similar.

Hope this clarifies,

Roger

>
> When one uses the native map - with unelided states - available from the URL
> below - then k-nearest neighbours also does not work properly in GeoDa.
>
>
>
> I also want to extend this to the SAMHSA substate shapefile found at this
> URL for the 395 substate areas used by the USA National Survey of Drug Use
> and Health within SAMHSA.
>
>
>
>
> <https://www.samhsa.gov/data/report/2014-2016-nsduh-substate-region-shapefil
> e>
> https://www.samhsa.gov/data/report/2014-2016-nsduh-substate-region-shapefile
>
>
>
>
> I did see that someone was able to create relationships across a straight
> for Italy although I am not quite sure how this was accomplished
> technically.
>
>
>
> I would be grateful for any help you could provide.
>
>
>
> Thankyou so much,
>
>
>
> Stuart Reece.
>
>
>
>
>
>                [[alternative HTML version deleted]]
>
>
>
> _______________________________________________
>
> R-sig-Geo mailing list
>
> <mailto:R-sig-Geo using r-project.org> R-sig-Geo using r-project.org
>
> <https://stat.ethz.ch/mailman/listinfo/r-sig-geo>
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo using r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

-- 
Roger Bivand
Department of Economics, Norwegian School of Economics,
Helleveien 30, N-5045 Bergen, Norway.
voice: +47 55 95 93 55; e-mail: Roger.Bivand using nhh.no
https://orcid.org/0000-0003-2392-6140
https://scholar.google.no/citations?user=AWeghB0AAAAJ&hl=en