[R-sig-Geo] Interpolating Count Data?

[Edzer Pebesma]

I think that if the counts are representative for a spatial support 
(area) or temporal support that does not vary, then you can consider the 
counts as an unscaled density and can interpolate. If they are 
representative for varying spatial/temporal support, I would avoid it, 
and first work towards a density estimate.

I cannot think of a reference to this.
--
Edzer

Hollister.Jeff at epamail.epa.gov wrote:
> All,
>
> I am reviewing some research in which a number of interpolations
> (Inverse Distance Weighting) were done on Species Abundance and Taxa
> Richness.  My gut and my memory suggest that interpolating count data is
> not acceptable.  After several hours of research I couldn't confirm
> this.
>
> My questions for the list are:
>
> 1.) Is it acceptable or not to interpolate count data?
>
> 2.) Are there any good references that state this?
>
> Thanks in advance your help!
>
> Cheers,
> Jeff
>
> ***************************
> Dr. Jeffrey W. Hollister
> US EPA
> Atlantic Ecology Division
> 27 Tarzwell Drive
> Narragansett, RI 02882
> (401) 782-9655
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>   

-- 
Edzer Pebesma
Institute for Geoinformatics (IfGI), University of Münster, Weseler
Straße 253, 48151 Münster. Phone: +49 251 8333081 Fax: +49 251 8339763
email: edzer.pebesma at uni-muenster.de http://ifgi.uni-muenster.de/