AI-GEOSTATS: Cokriging Estimation Variances
I have calculated estimates of my Primary variable every 1m over a grid of
60 x 60 x 1m (i.e. 3,600 estimates) using traditional ordinary cokriging. I
am using a 20 x 20m search for the Primary variable and 18 x 18m for the
Secondary variable, and a minimum of 4, maximum of 12 Primary and Secondary
I have 200 Primary samples, which are not gridded and are fairly evenly
distributed across the location. My Primary variable has a variance of
I have 300 Secondary data - 200 of which are 'co-located' with the Primary
variable, and the other 100 are 'independent' of the Primary dataset and are
also fairly evenly scattered across the location. My Secondary variable has
a variance of ~4.0.
My coregionalisation matrix satisfies the positive semi-definite
requirement, (with one zero eigenvalue in the nugget variance matrix)
My query relates to the pattern of estimation variances - I get 200 zero
variances at the Primary Sample locations (this I understand) - what I do
not understand is that I get 100 moderate estimation variances of
approximately ~1150 (1153 - 1160) at the 100 Secondary sample locations
without accompanying Primary values , and every other variance in the
location is the same value (2650).
Is this a sign that I am doing something wrong as I would have expected that
a non-gridded dataset would not give a constant estimation variance at
locations away from the sample locations? Is this phenomenon likely to be
exclusive to cokriging as I have not struck it before except in totally
EMAIL DISCLAIMER NOTICE - This message is the property of HATCH. The
information in this email is confidential and may be legally privileged.
It is intended solely for the addressee. Access to this email by anyone
else is unauthorised. If you are not the intended recipient, any disclosure,
copying,distribution or any action taken or omitted to be taken in reliance
on it, is prohibited and may be unlawful.
If you have received this message in error please notify HATCH immediately
via e-mail to : mailadmin@...
* To post a message to the list, send it to ai-geostats@...
* As a general service to the users, please remember to post a summary of any useful responses to your questions.
* To unsubscribe, send an email to majordomo@... with no subject and "unsubscribe ai-geostats" followed by "end" on the next line in the message body. DO NOT SEND Subscribe/Unsubscribe requests to the list
* Support to the list is provided at http://www.ai-geostats.org