s-news
[Top] [All Lists]

[S] Generalized local Geary statistic

To: s-news@wubios.wustl.edu
Subject: [S] Generalized local Geary statistic
From: Anne Dunning <adunning@MIT.EDU>
Date: Fri, 26 May 2000 14:59:31 -0400
Sender: owner-s-news@wubios.wustl.edu

I am a PhD student preparing for my oral examinations on Tuesday morning at 9am. I will present research I have done using the Local Indicators of Spatial Association from SPlus Spatial Statistics for ArcView. I am using the Geary statistic.

I realized I had a problem when my readings into the meaning of the Geary statistic said the values should be range from 0 to 2 with low values indicating high correlation. My values typically ranged well above two, and high values seemed to indicate places of high correlation. Page 112 of the online help file sarcview.pdf showed similar types of results with Geary values ranging from 0 to 24.30. It seems that the global Geary statistic works on the 0 to 2 scale, but the local Geary statistic does not have similar outputs.

For my exam on Tuesday, I need to understand the theoretical link between the global Geary statistic and the estimate from "generalized versions of the local Geary indicator of spatial association" mentioned in the S-Plus for ArcView help file for Local Spatial Association, but I cannot find the equation used for the local Geary in the SPlus documentation.

Can you help?

Your assistance will be sincerely appreciated.

-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu.  To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message:  unsubscribe s-news

<Prev in Thread] Current Thread [Next in Thread>
  • [S] Generalized local Geary statistic, Anne Dunning <=