nndist R vs. ArcGIS

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

nndist R vs. ArcGIS

smoluka
Can anyone tell me why I would get different average nearest neighbor values for the same set of coordinates between ArcGIS 10 and R? Sometimes the difference in distance is over 1.3 km.

Alexis

Reply | Threaded
Open this post in threaded view
|

Re: nndist R vs. ArcGIS

Curt Seeliger
Alexis wrote:
> Can anyone tell me why I would get different average nearest neighbor
values
> for the same set of coordinates between ArcGIS 10 and R? Sometimes the
> difference in distance is over 1.3 km.

spatstat::nndist calculates Euclidean distances rather than distances
along the earth's surface, which is probably what you're getting from AG.
A very short example illustrating the problem would be helpful in
determining if I'm at all right; on the other hand I'm glad you're testing
your results.

You might peek at the current thread "Geographic distance between lat-long
points in R" for more information.

cur
--
Curt Seeliger, Data Ranger
Raytheon Information Services - Contractor to ORD
[hidden email]
541/754-4638

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: nndist R vs. ArcGIS

barry rowlingson
In reply to this post by smoluka
On Mon, Apr 11, 2011 at 4:49 PM, smoluka <[hidden email]> wrote:
> Can anyone tell me why I would get different average nearest neighbor values
> for the same set of coordinates between ArcGIS 10 and R? Sometimes the
> difference in distance is over 1.3 km.

 Edge correction? In a spatial point pattern, points near the boundary
of your window are less likely to have a near neighbour because only
some of the surrounding space can possibly have points. I think
functions in spatstat will correct for this.

Make a simple test example and tell us what functions you are using.

And also try the r-sig-geo mailing list  for this sort of thing.

Barry

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: nndist R vs. ArcGIS

Rolf Turner-3
On 12/04/11 07:32, Barry Rowlingson wrote:
> On Mon, Apr 11, 2011 at 4:49 PM, smoluka<[hidden email]>  wrote:
>> Can anyone tell me why I would get different average nearest neighbor values
>> for the same set of coordinates between ArcGIS 10 and R? Sometimes the
>> difference in distance is over 1.3 km.
>   Edge correction? In a spatial point pattern, points near the boundary
> of your window are less likely to have a near neighbour because only
> some of the surrounding space can possibly have points. I think
> functions in spatstat will correct for this.
         No.  Not as far as I am aware or can discern.  The function
         nndist() does ***not*** invoke any edge correction.  It simply
         calculates the distances as they are, for the points that appear
         in the window, and takes the appropriate minima.

             cheers,

                 Rolf Turner
> Make a simple test example and tell us what functions you are using.
>
> And also try the r-sig-geo mailing list  for this sort of thing.
>
> Barry

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: nndist R vs. ArcGIS

smoluka
In reply to this post by smoluka
The problem was on the ArcGIS 10 end.  The program corrupted my layers.  I re-created the layer and now I get the same answer.  Thank  you all for your insight.  

Alexis

PS, the scale is in terms of owl territories and therefore 1.3 km is really huge.