[R-sig-Geo] Back-transforming krigged variables

[Edzer Pebesma]

Ebrahim Jahanshiri wrote:
> I am wondering if there is any function or option to back-transform the
> result of the lognormal kriging in gstat yet.
>   
You can use krigeTg, which does trans-Gaussian kriging for all Box-Cox 
transforms; passing it a lambda parameter with value 0, log-normal 
kriging is used. Pls look at the examples, the back-transformed values 
have funny names like var1TG.pred.

The whole think has been implemented for ordinary kriging only; if 
someone can point me out a source that describes how to do this for 
universal / external drift kriging, I'd be happy to look into how to 
implement it.
> Although for simple kriging it is fairly straight forward, that is, it is
> possible to do back-transform using the vector of predicted values and
> kriging variances, but for ordinary kriging, it might be difficult because
> we dont have lagrange multiplier (according to my web help search) to do the
> back-transformation. I am wondering if there has been any advancement in
> that matter?
>
> thank you
>
> 	[[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
>   

-- 
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster 
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251 
8333081, Fax: +49 251 8339763  http://ifgi.uni-muenster.de 
http://www.52north.org/geostatistics      e.pebesma at wwu.de