On Tue, 30 Jul 2002, Santiago Saura Martínez de Toda wrote:
> Dear list members,
> I have calculated the shared edges existing between each of the
> cover types (nine in this particular case) of a vector map.
> My objective is to determine, on the basis of this shared-edge analysis,
> which cover types tend to be associated (adjacent/contiguous/next)to each
> A simple table with the length of the shared edges for each two
> cover types is not too meaningful. For example, one of the cover types
> occupies about 70% of total landscape area, and thus the other cover
> types tend to share most of their edges with this dominant type. This
> (total edge shared) does not imply that there is a significant
> association (tendency for being located adjacent in the landscape). I
> tried to obtain a simple association measure that considered (corrected
> for) the effect of the different abundance of each of the cover types,
> but I don't feel really confident with the results I got.
> I wonder if there is available any association index or statistical test
> that determines whether a positive, negative or non-significant association
> exists between two given cover types in the landscape (preferably as derived
> from shared edges information). I guess this may be simpler to answer in
> raster than in vector spatial data.
Maybe a join count test, perhaps using the shared boundary length in the
weights matrix - Cliff, A. D., Ord, J. K. 1981 Spatial processes, Pion, p.
20. There is a version of the same colours (BB) test for R
(www.r-project.org) in the contributed package "spdep", and SpaceStat
(www.spacestat.com) also does it.
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Breiviksveien 40, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93
and: Department of Geography and Regional Development, University of
Gdansk, al. Mar. J. Pilsudskiego 46, PL-81 378 Gdynia, Poland.
* To post a message to the list, send it to ai-geostats@...
* As a general service to the users, please remember to post a summary of any useful responses to your questions.
* To unsubscribe, send an email to majordomo@...
with no subject and "unsubscribe ai-geostats" followed by "end" on the next line in the message body. DO NOT SEND Subscribe/Unsubscribe requests to the list
* Support to the list is provided at http://www.ai-geostats.org