[R] Spatial Statistics: surf.gls

[Prof Brian Ripley]

On Fri, 19 Mar 2004, Stegemann, Berthold wrote:

>  In an experimental setup we obtain z-data samples at equidistant grid points.
> 
> The surf.gls (Kriging) algorithm produces an error under this
> circumstance when performing the Choleski decomposition.
> 
> A workaround is to dither the grid coordinates using  
(x <- rnorm(length(x)) ; y<- rnowm(length(y))).

That's not dithering but changing them completely.
Hint: ?jitter.

> Question: Is this an expected behaviour  of the  surf.gls function ?

No, and it has been tested under those circumstances.  Did you adjust the 
accuracy of the approximation via nx?  Is your covariance model actually a 
valid one?

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595