[R-sig-Geo] Fitting a STvariogram

[Benedikt Gräler]

Dear Alexandre,

currently, the parameter "anis" in one of the building blocks of a 
spatio-temporal variogram model is not supported. The spatio-temporal 
anisotropy (e.g. in a metric model) is part of the spatio-temporal 
variogram model definition ("stAni"), see ?vgmST for available models 
and parameter definitions.

We do not provide special plotting functions to fit the spatio-temporal 
anisotropy. However, the demo(stkrige) will show levelplots for sample 
and model variograms and bring up an interactive "lollipop3d"-plot 
(based on the rgl package) to visually judge the overall variogram fit.

The function fit.StVariogram will minimize (using optim) all parameters 
(incl. stAni where part of the model) in terms of the residuals between 
sample and model variogram.

I hope this helps. Best wishes

  Ben


On 25.02.2013 11:34, alexandre.champendal at unil.ch wrote:
> Hello,
>
> I am working with spacetime data of pollution (91 stations, 193 time).
> With the new release of gstat, i was able to compute a good sample
> variogram (thanks :-)).
You're welcome; it is always nice to see code being used.

>
> But now I would like to now if there is a way to visualize our data set
> in order to be able to define a good Space-Time anisotropy !? I
> understand the variable we have to
> set: anis = c(p,q,r,s,t), but i am not able to find a good way to find
> the parameters.
>
> How can we do this?
>
> Thanks a lot.
>
> Alexandre
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Benedikt Gräler

ifgi - Institute for Geoinformatics
University of Muenster

http://ifgi.uni-muenster.de/graeler

Phone: +49 251 83-33082
Mail: ben.graeler at uni-muenster.de