[R-sig-Geo] Cluster identification using space-time permutations

[Jesse Whittington]

Hi Virgilio,

I tried your DCluster package earlier with the aid of Roger's book
Applied Spatial Data Analysis with R. I'd still like to try your code
for spatio-temporal clustering.  It's probably OK if the algorithm is
not fully tuned as I expect to get false positives.

Thanks for your help,

Jesse


2010/8/30 Virgilio Gómez-Rubio <Virgilio.Gomez at uclm.es>
>
> Dear Jesse,
>
> You can look at the functions in the DCluster package for the (purely)
> spatial scan statistic. You could start from there. I have also some
> other code for spatio-temporal clustering that I have not yet released
> (and I believe that the permutation algorithm may not be tuned) but I
> will be happy to share it with you.
>
> Best,
>
> Virgilio
>
> El lun, 30-08-2010 a las 12:35 -0600, Jesse Whittington escribió:
> > We've been using the SatScan space-time permutation scan statistic to
> > identify potential predation sites (ie clusters) from wolf GPS data. Are
> > there functions that I could use in R to run this cluster analysis?
> >
> > Here's the reference:
> >
> > Kulldorff et al. 2005 A Space Time Permutation Scan Statistic for Disease
> > Outbreak Detection
> > http://www.plosmedicine.org/article/info:doi/10.1371/journal.pmed.0020059
> >
> > I've searched the RSiteSearch many times without luck.  Any help would be
> > greatly appreciated!
> >
> > Jesse Whittington
> > Wildlife Biologist
> > Banff National Park
> >
> >       [[alternative HTML version deleted]]
> >
> > _______________________________________________
> > R-sig-Geo mailing list
> > R-sig-Geo at stat.math.ethz.ch
> > https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>