Hey, here's a new topic.
I'm doing some small area analysis on low demand housing and I want
to smooth out the 'outliers' and extreme values so that I can produce
a map that shows continuous neighbourhoods of unpopularity rather
than a chaotic clustering of EDs (enumeration districts). I've
managed to produce some maps using an aggregated 'unpopularity
index' which compares all the scores to the nearest neighbours of an
ED.
Are there any geographers out there that can tell me whether there
are papers discussing the methodological flaws with this application
and its limitations. I guess in this application it has some
validity as 'rogue' EDs maybe a product of a number of statistical
artefacts but people may see an area as unpopular because of its
'adjacency'.
Cheers
Peter
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Peter Lee
Centre for Urban and Regional Studies (CURS)
The University of Birmingham
Pritchatts Road
Edgbaston
Birmingham
B15 2TT
UK
Tel (+44) 121 414 3645
Fax (+44) 121 414 4989
http://www.bham.ac.uk/curs/
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|