[R-sig-Geo] warnings in fit.variogram and autofitVariogram

[Pierre Roudier]

Hello Kad,

The best thing to do is probably to actually *read* those warnings.

It is not that clear what models you tried to fit, but basically I
guess you tested the full range of models available through gstat (see
vgm()). One of them (the bessel model) does not fit using the tested
parameters. It has been excluded.

The second warning is related to that : some models have been excluded
because they had a negative sill and/or range and/or nugget value
fitted.

Now I suggest you to try to dig a bit more the doc and understand what
the autoKrige function is actually doing (i.e. computing an
experimental semi-variogram, then fitting a model, then use it in a
kriging routine).

Pierre

2010/8/24 kad <kadraamrane at hotmail.fr>:
>
> Dear all,
> yesterday I posted two messages by mistake,excuse me everybody.
> I see two warnings and I dont know what I must do.
>  I want to make a ordinary kriging.
>  I use the package automap for my report .do you help me?Thanks
>
> 1) In fit.variogram(object, model, fit.sills = fit.sills, ... :
>  valeur d'argument hors intervalle dans 'bessel_k'
>
> 2) In autofitVariogram(ANGAR ~ 1, r) :> Some models where removed for being
> either NULL or having a negative> sill/range/nugget,> set verbose == TRUE
> for more information
> My code is: http://r-sig-geo.2731867.n2.nabble.com/file/n5454757/mycodeR
> mycodeR
>
> when I do verbose=TRUE I see this:
> http://r-sig-geo.2731867.n2.nabble.com/file/n5454757/error error
> --
> View this message in context: http://r-sig-geo.2731867.n2.nabble.com/warnings-in-fit-variogram-and-autofitVariogram-tp5454757p5454757.html
> Sent from the R-sig-geo mailing list archive at Nabble.com.
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>