Re: AI-GEOSTATS: Significant Moran's I?
- On Thu, 10 Jul 2003, Russell Barbour wrote:
> To measure auto-coorelation Moran's I is compared to the expected "I" thatI guess that will depend on your specific application. If you permute your
> would be generated from a random distribution. My question is if the observed
> Moran's I is more than one standard deviation higher than expected "I" could
> that be considered significant auto-correlation?
observed values about your spatial units, you can work out how far out in
one of the tails your observed statistic falls. Where you want to set your
bound for a significant statistic is then a matter for your judgement,
although +1SD sounds permissive. Recall that Moran's I can also detect
non-stationarity, so is a general test for spatial mis-specification
(Fingleton, 1999, Journal of Regional Science).
>Economic Geography Section, Department of Economics, Norwegian School of
> Russell Barbour Ph.D.
> Research Associate in Applied Mathematics
> Vector Ecology Laboratory
> Yale School of Medicine
> 60 College St. Rm 600
> New Haven CT. 06520
> TEL: 203 785 3223
> FAX 203 785 3604
> email: russell.barbour@...
Economics and Business Administration, Breiviksveien 40, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93
* 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