[R-sig-Geo] DCluster questions

James Rooney ROONEYJ4 at tcd.ie
Fri Sep 6 17:15:32 CEST 2013

Hi all,

I'm wondering if I can get a little advice on using DCluster.
I have produced a map of areal incidence rates and I'd like to try and detect clusters.
I have also implemented Bayesian smoothing and have therefore pre and post smoothing maps.

I have some code as follow for detecting clusters using the Kuldorff-Nagarwalla analysis (code based on Fig11.18 in the ASDAR book and this useful question and answer: http://r-sig-geo.2731867.n2.nabble.com/Strange-results-in-DCluster-package-td7326832.html )

# get centroids of polygons

#Create the data frame demanded by DCluster
sa<-cbind(sa, Expected=mean(Areas$exp))
sa<-cbind(sa, x=Areas$x, y=Areas$y)

#Kuldorff-Nagarwalla analysis
mle<-calculate.mle(sa, model="poisson") 
knres<-opgam(data=sa, thegrid=sa[,c("x", "y")], alpha=.1, R=20,
             iscluster=kn.iscluster, fractpop=.10, model="poisson", mle=mle, log.v=TRUE)

This seems to work ok however there are a few things I'm confused on:
1) Should I be using this algorithm on my incidence rates pre or post Bayesian smoothing ? I'm thinking that the mle expression above includes a smooth (do I understand that correctly ?) - but I' prefer to utilise my hard-won Bayesian smooth if possible.

2) Will opgam/kn.iscluster only detect "hotspots" or will they also detect "coldspots" i.e. areas of statistically unlikely lower incidence rates ?

3) I'm not familiar with bootstrapping - how many bootstraps should I be running and why (i.e. - what should I set R to) ?

4) How do I decide what the correct value for fractpop is ? I initially had it set to .25 and I was getting cluster of 50% of my cases which made no sense.

5) Is there any correction for multiple testing in the opgam() command ? I have over 3000 areas - do I need to set a very low alpha ?

I would be grateful for any enlightenment anyone may have to pass on :)

Many thanks,

More information about the R-sig-Geo mailing list