[R-sig-Geo] fix the value of nugget

[Edzer Pebesma]

On 09/09/2015 01:09 PM, Sherien Al-Azerji wrote:
> Dear All,
> 
> I'm running Universal kriking method and I need to set the value of nugget
> in the variogram model to zero even after fitting a variogram, I need the
> fitted variogram to have a zero nugget. How can I do this please.

Showing what you've tried would help. Assuming you use package gstat,
you can pass a variogram model without nugget (e.g. vgm(1, "Exp", 300) )
to fit.variogram, and no (=zero) nugget will be fitted.

> 
> another question please, some times when I run my code I get this error
> message (LDL factor) what this mean? and how can I solve it.

It means the covariance matrix is (too close to) singular; this happens
if you have (nearly) duplicate observations, or a variogram model that
gives rise to (nearly) perfectly correlated observations, such as the
Gaussian model.

> 
> Best Regards
> Sherien
> 
> 	[[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,
Heisenbergstraße 2, 48149 Münster, Germany; +49 251 83 33081
Journal of Statistical Software:   http://www.jstatsoft.org/
Computers & Geosciences:   http://elsevier.com/locate/cageo/
Spatial Statistics Society http://www.spatialstatistics.info