[R-sig-Geo] predict.gstat and LDL factor error

[Edzer Pebesma]

The memory will not be the problem, that would give a different error
message. Also, zero distance between observation and prediction
locations should not be a problem.

The distance in metres is not sufficient information, as the singularity
problem is in the covariance matrix or in the design matrix. Do you have
observations with identical locations? How large is the area? Which
variogram model did you specify? Did you specify a trend?

On 01/11/2011 12:14 PM, Veronesi, Fabio wrote:
> Dear All,
> I'm trying some simulation with my data.
> I set the gstat object and the newdata (in a data frame format) but when I start the simulation with the function predict.gstat it return the LDL error.
> Now, I check the distance between observation and prediction location with the function zerodist and the minimum is 10 metres, so it should not be the problem. My data are 30 observation and I'm trying to simulate in 94 location, therefore with a 32bit machine and 4Gb of available RAM also the memory should not be a problem.
> What could it be then?
> Many thanks for any help,
> Fabio
> 
> 
> Mr. Fabio Veronesi
> Ph.D. student
> Cranfield University
> 
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> 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