[R-sig-Geo] Empirical Bayes smoothing (DCluster)

Dorothea Lemke dorothea.lemke at uni-muenster.de
Mon Oct 14 14:53:39 CEST 2013


Dear Virgilio,

many thanks for your fast response - this helps a lot. I have another
question concerning the
EBlocal-function: Is there a way to calculate the confidence interval
for the risk estimates?

Thank you very much in advance
Dorothea

Virgilio Gómez-Rubio schrieb am 2013-10-10:
> Dear Dorothea,


> > I have used both of the empirical Bayes smoothing models
> > (Poisson-Gamma and
> > Log-normal) implemented in the package DCLuster for smoothing
> > disease risk
> > in
> > a study region.
> > But I wonder if there is a function where the local mean can be
> > used
> > instead of
> > the global mean in order to smooth the estimates.

> You can use EBlocal() in spdep to achieve local smoothing.

> Best wishes,

> Virgilio

> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Dorothea Lemke
Institute for Epidemiology and Social Medicine
Albert-Schweitzer-Campus 1, Building D3
D-48149 Münster

Fon: +49(0)251/83 58338
Email: dorothea.lemke at uni-muenster.de



More information about the R-sig-Geo mailing list