I'm still not entirely sure what you're getting at:  spatial correlation
of origin/destination locations to each other?  Or some characteristic
of the origin/destination pairs?  It sounds like the latter, but then
the question is "correlated with what"?

 

The choice of method is ultimately driven by the conceptual model of the
phenomena, which is what those questions are getting at.  If you can
answer those questions with some precision, finding an analytic method
that can implement the resulting model is fairly straightforward.

 

If you're still trying to sharpen your thinking (or even if you think
you have the abstractions nailed down and are just looking for
corresponding methods), I'd recommend starting with the "spatstat"
package (e.g. via the website www.spatstat.org) and following its
reference list into the world of spatial statistics.

 

If you're actually interested in stolen cars, you might take a look at
CrimeStat (http://www.icpsr.umich.edu/CrimeStat/) which rolls up
implementations of a lot of spatial statistics techniques that could be
applicable in tracking crimes and finding criminals.  The software is
"free as in beer" but it is not implemented in R (though I suppose one
might be able to wrap the provided library functions).  The various
analytic methods are mostly standard and reasonably well documented, so
any given analysis could be quite readily reproduced in the statistical
system of your choice.

 

I hope that helps!

 

Jeremy Raw, P.E.

FHWA Office of Planning

[email protected]

(202) 366-0986

 

From: Rich Heimann [mailto:[email protected]] 
Sent: Wednesday, October 12, 2011 7:26 PM
To: Raw, Jeremy
Cc: [email protected]
Subject: Re: [R-sig-Geo] Correlation between O&D

 

Great! I hope you can tell me more. 

I am considering origin and destination to be linked data... Such as a
stolen car and a recovered car - rather than an independent point
pattern. I hope that clears things up? 

Regards,
Rich

Rich Heimann

 Tel: (571) 403-0119 
[email protected] 

 

 

On Wed, Oct 12, 2011 at 3:16 PM, <[email protected]> wrote:

It all depends on what you mean by "origin and destination data".
Assuming I am allowed to make up my own definitions, the answer is
definitely "yes" :-)

My advice is to be somewhat more specific about the problem domain.

Jeremy Raw, P.E.
FHWA Office of Planning
[email protected]
(202) 366-0986 <tel:%28202%29%20366-0986> 


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Rich Heimann
Sent: Wednesday, October 12, 2011 2:24 PM
To: [email protected]
Subject: [R-sig-Geo] Correlation between O&D


Hello all,

I want to know if the list is aware of a way to determine whether origin
and
destination data is correlated - rather than looking at each as
independent?
Any advise?

Thanks,
Rich

Rich Heimann

 Richard Heimann | ITT Corporation | T: 571.403.0119 |
[email protected]
Richard Heimann | University of Maryland, Baltimore County | T:
571.403.0119
| [email protected]

Contact Me <http://www.linkedin.com/in/rheimann>
LinkedIn<http://www.linkedin.com/in/rheimann>
<https://twitter.com/rheimann> Twitter <https://twitter.com/rheimann>
<https://plus.google.com/117471169530873553158> Google
Plus<https://plus.google.com/117471169530873553158>

Chat [image: Google Talk] heimann.richard [image: Skype] heimann.rich

 [image: Twitter] <http://twitter.com/rheimann> Latest tweet: An

Intuitive
Explanation of Bayes' Theorem: http://t.co/6DAh8O43

Follow @rheimann <http://twitter.com/rheimann> Reply
<http://twitter.com/?status=@rheimann%20&in_reply_to_status_id=123943215
412953090&in_reply_to=rheimann
<http://twitter.com/?status=@rheimann%20&in_reply_to_status_id=123943215
%0A412953090&in_reply_to=rheimann> >
Retweet
<http://twitter.com/?status=RT%20%40rheimann%3A%20An%20Intuitive%20Expla
nation%20of%20Bayes%27%20Theorem%3A%20http%3A%2F%2Ft.co%2F6DAh8O43>
 22:08 Oct-11<http://twitter.com/rheimann/statuses/123943215412953089>
 Get this email app!
<http://www.wisestamp.com/apps/twitter?utm_source=extension&utm_medium=e
mail&utm_term=twitter&utm_campaign=apps
<http://www.wisestamp.com/apps/twitter?utm_source=extension&utm_medium=e
%0Amail&utm_term=twitter&utm_campaign=apps> >


 Please consider your environmental responsibility. Before printing this
e-mail message, ask yourself whether you really need a hard copy.

       [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo



<<image001.jpg>>

_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Reply via email to