GEOSTATS: Summary: Positive definiteness for collocated cokriging
- Pierre Goovaerts answered my question about semivariogram modelling for
collocated cokriging as follows:
Since you usually do the modeling in terms of
semivariogram instead of covariance, I would
say that the only
constraint your linear model of coregionalization
must satisfy in collocated cokriging is:
|sill_ZY|<=sqrt(sill_ZZ x sill_YY), which implies
that sill_YY >= (sill_ZY)^2/sill_ZZ.
You can check that, whatever the relative contribution
of the different basic structures to the sill_YY,
collocated cokriging will yield the same estimates.
Sytze de Bruin
Centre for Geo-Information
P.O. Box 339
6700 AH Wageningen
Tel: +31 317 474636
Fax: +31 317 474567
*To post a message to the list, send it to ai-geostats@....
*As a general service to list users, please remember to post a summary
of any useful responses to your questions.
*To unsubscribe, send email to majordomo@... with no subject and
"unsubscribe ai-geostats" in the message body.
DO NOT SEND Subscribe/Unsubscribe requests to the list!