I made a program which calculates p-value of
spatial correlation between two variables(Xi, Yj),
following some advices which I obtained from ai-geostats,
( Bi-variate Moran's I).
This program uses inverse distance( 1/r )
for weighting ( Wij ).
However, if the above two variables
are always sampled at same points,
Wij will be +infinite for Xi,Yi and
the correlation will not be 'spatial'.
How can I cope with r=0 ?
There seems to be following solution;
(1)categorize distance into finite classes.
(2)Take only Xi, Yj ( i != j ) into calculation
(3)Adopt different weighting strategy
I would appreciate your suggestion of any kind.
Yoshiro Nagao ( Y-Nagao )
*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!