Hi Josh,
Take a look at the section on BLAS in the R Installation and Admin manual.
In Linux we've gotten order of magnitude speedups by using GotoBLAS instead of
the default BLAS in R. But it's not available for XP - there are other BLAS
implementations mentioned in the manual that might
Here's a one-day course: http://www.stat.purdue.edu/envr/shortcourse.html
chris
--
Chris Paciorek / Asst. ProfessorEmail: [EMAIL PROTECTED]
Department of Biostatistics Voice: 617-432-49
This is a bit of a distant memory from a few years back when I also was trying
to better understand what ArcGIS was actually doing, but I believe there is
some, though probably not a large amount of, additional technical detail
available in the following ESRI manuals:
Johnston, K. et al. 2001.
If you want to avoid zero distances, what Edzer meant is to actually jitter the
points and then recalculate the distance matrix based on the new locations.
Replacing the zeros doesn't give you a valid distance matrix because it doesn't
account for having moved the two points with respect to all
Hi Stéphane,
For US locations, you might try www.nationalatlas.gov, click on MapMaker (upper
left) and then 'Find' (upper right).
It allows you to search by name of geographic features. I've found some small
ponds by name and state using this.
-chris
Hi Hywel,
I'm not familiar with 'spatial' but you might look at the variogram tools in
'geoR'. This should allow you do look for anisotropy - I believe the function
is vario4.
You should be able to check empirically if the variogram is on the residuals by
comparing variogram with surf.ls with
I might consider using gam() in R to smooth the 0/1 indicator for each class
individually based on a Bernoulli model - doing each class individually. A
downside of course is that the resulting smoothed maps of the proportions for
each class would not add to one at an individual location, but th
