GEOSTATS: GEOSTAT: Exponential models in S-Plus and GEOEAS
- This mail message, and any attachments, has been checked for Viruses
by ADAS before dispatch to the Internet.
Text: (38 lines follow)
Since sending my first email about the problem I have been having with
fitting exponential models in both geoas and s-plus, I have noticed that by
changing the exp.vgram function in S-Plus
nugget + sill * (1 - exp( - distance/range))
(which is often quoted as the exponential model, e.g. Haining p 97)
to the following (which resembles that of Isaaks and Srivastava, page 374),
nugget + sill * (1 - exp( - (3 * distance)/range))
I then got the same fit as that in GEOAS.
I am confused by this - and it seems a bit dangerous if different software
uses different models, because we quote the semivariogram parameters and not
the model format.
Hope someone can help on this one -
Dr Alison Riding
Tel: +44 (0) 1902 693129
Fax: +44 (0) 1902 693166
Use Proportional Font: true
*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!