On Mon, 2003-05-05 at 03:40, Yan Yu wrote:> Greetings, all:
> I am wondering have anyone used package "sgeosta" before,
> I have a Q about its variogram fitting function:
> fit.exponential, fit.gaussian and fit.wave
>
> they ask for a few parameters, which I have no clue how to set them..
> e.g., they list this example:
> maas.vmod<-fit.gaussian(maas.v,c0=60000,cg=110000,ag=800,plot.it=TRUE,
> iterations=30
>
> In the manual page, they list the meaning of those paramters that have
> model dependent meanings:
>
> c0: initial estimate for nugget effect, valid for
all
> variogram types, partial sill (cX) and
> (asymptotical) range (aX) as follows:
> ce, ae
> initial estimates for the exponential variogram
> model
> cg, ag
> initial estimates for the gaussian variogram model
> cs, as
> initial estimates for the sperical variogram model
> cw, aw
> initial estimates for the periodical variogram
model
>
> Sorry for my ignorance on those models, my Qs is:
> 1) what is the rule of thumb to set the above parameters?
> 2) Does it really matter how I set those initial estimates? How much
> influence the initial parameter setting is going to have on the final
> model fitting?
> 3) How do I know if I set those parameters right or way off?
>
> thanks a lot!
> yan
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Hi
Those are the parameters of the variogram function you want to adjust.
See some reference about spatial stats like "Statistics for Spatial
Data" from Cressie (1993) or "Spatial Statistics" from Ripley
(1981).
Usually you should get an ideia of that parameters looking at the
empirical variogram.
EJ