In addition to Pierre s comments on the risks of extrapolating, I also got the two following replies Lynn J. Torak Perhaps the border effect is caused by anMessage 1 of 1 , Mar 24, 2003View SourceIn addition to Pierre's comments on the risks of extrapolating, I also got the
two following replies
Lynn J. Torak
"Perhaps the "border effect" is caused by an ill-conditioned matrix
presented to either the direct or iterative solver of the geostat program,
causing an oscillation in the solution."
Dan W. McCarn
"Just a thought, but perhaps the solution matrix is getting more and more
"ill-conditioned" away from the center of the data set resulting in "unstable"
solutions when the precision of the computer is marginal (say 32-bit
floating-point numbers). I know that in one benchmark data set that I used,
the results were up to 20% off the "true" values calculated at 64-bit and
128-bit precision. This resulted in negative numbers where there should have
Thanks a lot to all for the kind support.
* 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