[R-sig-Geo] How to deal with data points having the same lat long position?

[Clint Bowman]

Jose,

Sorry I wasn't sufficiently clear.  Because your data has only zip codes 
for location, you've merged in the centroid (lon.lat) for each zip code 
into your dataset.  Then after averaging within each zip code you will 
have just a single value for each zip code and the (lon,lat) coordinates 
associated with it.  Now you can construct your variogram and continue 
with your analysis.  You will lose any information that the intra-zip code 
variability could contribute.

Clint

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 Fri, 5 Sep 2014, José Luis Rotundo wrote:

> Thanks Clint. I could try that. But I wanted to have data by lat and long location. 
> Best regards,
> 
> Jose
> 
> 
> 
> 
> 2014-09-05 17:13 GMT-03:00 Clint Bowman <clint at ecy.wa.gov>:
>       Jose,
>
>       Are your units of yield in quantity/area or total quantity?  If yield is quantity/area, I think I would compute the average for each county with a
>       reported yield.
>
>       Clint
>
>       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 Fri, 5 Sep 2014, Christopher Swingley wrote:
>
>             Jose,
>
>             On Fri, Sep 5, 2014 at 10:29 AM, José Luis Rotundo <jrotundo at unr.edu.ar> wrote:
>                   I am working with a database of farm yields across USA and the objective is
>                   to map soybean yields. To preserve the identity of the farmers, they only
>                   provided the zipcode of the farm. Then I attached the zip code lat and
>                   long. The problem I have is that several farms belongs to the same zipcode
>                   and therefore they have the same lat and long. Having this repeated
>                   locations troubles the construction of the variogram.
> 
>
>             Wouldn't it be better to attach the sum of the soybean yields assigned
>             to a zip code to a vector layer containing zip code boundaries?  I can
>             imagine that if you assign values to a single point (even jittered
>             when there are duplicates for single zip code) per zip code, that you
>             won't wind up with a very accurate representation of the spatial
>             pattern because the area each zip code covers will be different.
>
>             Cheers,
>
>             Chris
>             --
>             Christopher Swingley
>             Fairbanks, Alaska
>             http://swingleydev.com/
>             cswingle at swingleydev.com
>
>             _______________________________________________
>             R-sig-Geo mailing list
>             R-sig-Geo at r-project.org
>             https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 
> 
> 
> 
> --
> 
> 
> José L. Rotundo
> CONICET
> Facultad de Ciencias Agrarias
> Univ. Nacional de Rosario
> Zavalla, Santa Fe
> Argentina
> 
>