ai-geostats  

Re: AI-GEOSTATS: clustering of locations vs locations data

Pierre Goovaerts
Thu, 15 Apr 2004 08:37:22 -0700

Dear Simon,

I would recommend that you look at the cluster advisor
that is available on the following webpage:
http://www.terraseer.com/products/csr/clusterseer_advisor.html
This will guide you among the tests available to detect clusters
in space, time and space-time at a global, local or focused level.

If you look at the detection of clusters in space, you will find
the following definition:
Ripley's K-function is used to analyze the spatial pattern of point data.
It can detect global spatial clustering in individual-level data. In
essence, you can use it to compare the observed pattern of cases with that
generated by a homogenous Poisson process.

An alternative is the Besag and Newell's method:
This method scans the data for collections of cases that appear to be
unusual clusters. To do so, it centers a circular window on each region in
turn. This window is then expanded to include neighboring regions until
the total number of cases in the window reaches a user-specified
threshold, k. Then, the population size inside the window is compared to
that expected under an average or expected disease frequency.

Examples and references are provided, which should help you selecting the
correct method.

Pierre

<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>

Dr. Pierre Goovaerts
President of PGeostat, LLC
Chief Scientist with Biomedware Inc.
710 Ridgemont Lane
Ann Arbor, Michigan, 48103-1535, U.S.A.

E-mail:  [EMAIL PROTECTED]
Phone:   (734) 668-9900
Fax:     (734) 668-7788
http://alumni.engin.umich.edu/~goovaert/

<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>

On Thu, 15 Apr 2004, Simon Berlage wrote:

> Hello Geostatters,
>
> I have various monitoring sites in an area. Before determining whether the
> DATA is clustered or not, I would like to know if the sample locations (x,y)
> are clustered (otherwise whats the point if detecting clusting in your data?!).
>
> I understand that I should be able to tell by just looking at the spatial
> distribution
> of the monitoring points. But in my case its not really clear whether the
> locations could be considered as clustered or not. Its for this reason I
> would like
> a formal unbiased expression of clustering/non-clustering.
>
> I have looked at the Ripley's K function but (correct me if I am wrong) this
> concentrates on clustering issues of the data and not the location of the
> data points locations in space. I have read about nearest neighbour analysis
> whereby you input the site coordinates and set their attribute values to
> 1. Any output Z-value should indicate the degree of randomness of the sample
> locations and hence the degree of clustering. I fail to understand where
> the criteria for random vs. non random distribution come from? but that's
> not the the point here and I shall (try to) refrain from hassling you about
> this.
>
> What's more important is the recommended statistic to use for this, what
> statistic has the greatest consensus?
>
> Thank you,
> Simon
>
>
> _____________________________________________________________________
>
> Bent u toe aan sneller en goedkoper internet?
> Ga dan naar http://adsl.tiscali.nl
>
>
>
> --
> * To post a message to the list, send it to [EMAIL PROTECTED]
> * 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 [EMAIL PROTECTED] 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
>

--
* To post a message to the list, send it to [EMAIL PROTECTED]
* 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 [EMAIL PROTECTED] 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