GEOSTATS: GSLIB indicator kriging
I'm fairly new at much of these geostatistics, but am trying to incorporate
using them into my thesis. My project involves creating vegetation maps
from point data. I had come to the conclusion that I needed to use
indicator kriging since I am working with categorical data. My plan was to
use GSLIB for this indicator kriging, since S-Plus (the other software I
have access to) does not have this option.
When reading the GSLIB User's Manual I noticed that it said that "IK of
categorical variables can be done by directly applying okb2d [the ordinary
kriging algorithm]...". (Page 76 in my version of the text.) This seems
counter intuitive to me. If my variables are already in categorical form
(0's and 1's) can I use any ordinary kriging? Why am I not supposed to use
indicator kriging? I thought that indicator kriging was different from
ordinary kriging in that it is specifically designed to work with this type
of data (at least this was the advice given to me with someone with more
knowledge than I).
If anyone could help clarify my confusion I would greatly appreciate it.
Department of Forestry
University of Wisconsin-Madison
*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!