Re:

["D. Karssenberg" <d.karssenberg@geog.uu.nl>]

At 11:41 AM 8/10/99 -0600, you wrote:
>
>Dear Netters;
>Can anyone explain to me how the coefficients of the variogram model is
>calculated.
>Thanks!
>Kanishka Perera
>
>

In general there are two ways to fit the variogram model to the experimental
variogram (data) points:
1) manually
Just change the parameters by trial and error until you get a good fit. It
sounds not too scientific, but it is quite often done
2) automatic fitting
Use an automatic fitting method. E.g. (weighted) least squares fitting which
is included in gstat (check out the manual for the fitting methods
provided). It is often needed to fix (ie exclude from fitting) the nugget or
range parameter(s) to get a better fit, see the on line gstat manual.

Cheers, Derk Jan

--

Derk Jan Karssenberg
PCRaster
Faculty of Geographical Sciences
Utrecht University
PO Box 80.115
3508 TC Utrecht
the Netherlands
Phone:  (+31) 30 2532768
Fax:    (+31) 30 2531145
E-mail: d.karssenberg@geog.uu.nl
http://www.frw.ruu.nl/pcraster.html