[R-sig-Geo] Normal score transformation

[Ashton Shortridge]

Hi Laura,

I've written code to do normal score and back-transforms. Edzer dropped this 
code from me last month on this list, but I'll repost.

Normalizing data is extremely simple in R. The back-transform is the 
problematic part. Please read the documentation in the file to learn more 
about these issues and to help determine if what I wrote is useful for you.

The URL for the normal score code is:
http://www.msu.edu/~ashton/temp/nscore.R

Yours,

Ashton

-- 
Ashton Shortridge
Associate Professor			ashton at msu.edu
Dept of Geography			http://www.msu.edu/~ashton
235 Geography Building		ph (517) 432-3561
Michigan State University		fx (517) 432-1671

On Tuesday 08 July 2008, Laura Poggio wrote:
> Dear all,
> I have a small image with three bands and I would like to normalise the
> variance of the three bands in order to get a more homogeneous dataset for
> further elaborations.
> I am thinking to use the normal score transform, but I have some questions
> about how to implement in R and especially how to do with raster data.
> My data are read into R with the readGDAL function.
>
> I have been trying the qnorm() and the qqnorm(ppoints()) with strange
> results, using on data.frame or matrix or vector types: in any case all
> values are NAs.
>
> Any suggestion on which is the most suitable function to do the transform
> on raster data within R would be really appreciated.
>
> Thank you very much in advance
>
> Laura
>
> 	[[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