[R-sig-Geo] Spatial Regression: Moving window regression (MWR) or GWR adaptation...?

[Clint Bowman]

Isn't this amenable to a Poisson point process 
<http://en.wikipedia.org/wiki/Poisson_process>?

See Konisky, et al, 2013, "Strategic Placement of Air Polluters: An 
Application of Point Pattern Models".


Clint Bowman			INTERNET:	clint at ecy.wa.gov
Air Quality Modeler		INTERNET:	clint at math.utah.edu
Department of Ecology		VOICE:		(360) 407-6815
PO Box 47600			FAX:		(360) 407-7534
Olympia, WA 98504-7600

         USPS:           PO Box 47600, Olympia, WA 98504-7600
         Parcels:        300 Desmond Drive, Lacey, WA 98503-1274

On Wed, 31 Jul 2013, Juan Manuel Becerra wrote:

> Hi
>
> I'm trying to make a model to estimate the number of roberys. I know the
> address of these people and the point on the map where they live. I have a
> sample of all the country, in different cities, different zones. The
> variable can be set to 0,1,2 .....,and it is distributed as a poisson.
> Right now I'm using data from the population density from a raster of
> european environment agency. For now I want only estimate the number of
> roberys, depending on population density, or moving window arround the
> people live. In future I would like to include more variables raster-based
> style.
>
> I have read that the models used in these cases are GWR, but in a book
> specifically speaks about MWR as a good method to estimate in places where
> you did not have data to make the regression (this is my situation). I
> think GWR need points near the value estimate to give a good estimate. In
> my case i don't have these points to estimate because I want to estimate
> only considering adaptations of independent variables (...focal by kernel,
> or others ).
>
> I've read about GWmodel, gwrr, spgwr .... but I don't have a very clear
> idea about what is the best way in my case. Is there any package that has
> implemented MWR?, It is possible that I'm wrong, and I can use whith GWR
> raster values in areas without sample to estimate?. A good
> recommendation?... i'm new in this king of regressions.
>
> I posted the same question in gis secction of stackoverflow.
>
> http://gis.stackexchange.com/questions/67443/moving-window-regression-mwr-in-r
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>