topic Best way to define search radius for Kernel density analysis in ArcGIS Spatial Analyst Questions

Best way to define search radius for Kernel density analysis

CatrionaBrogan — Thu, 19 Jan 2012 14:03:22 GMT

Hi,
I'm new to GIS so this is probably pretty simple stuff. I have a set of co-ordinates and I am doing kernel density on it. Rather than randomly just picking an arbitrary search radius is there any way that I can find out what the most appropriate search radius is for my points? I have 20 different categories and they are all quite different in their distribution patterns so I am wary of just applying the same search radius to them all.
Thanks.

Re: Best way to define search radius for Kernel density analysis

PeterMarkus1 — Mon, 26 Nov 2012 16:19:48 GMT

Hi I´m althoug not a GIS expert an my englisch is not very good. Please excuse me!

But I have done these question today in compination with these tow ESRI video tutorials:
http://video.arcgis.com/watch/401/performing-proper-density-analysis
(the hole video)
http://video.esri.com/watch/903/spatial-statistics-best-practices
(only the first 16 min.)

And with the "Incremental Spatial Autocorrelation" (Toolbox)

I don´t know if it is perfect but I think it´s ok.

Can anyone here give me a feedback if:
1.) it is right to use the "Incremental Spatial Autocorrelation" (Toolbox) searching for the best search radius in density analysis (for the density of the number of observations for house prices - I have point data and want to know the density per point of a unit)?
2.) I have realy problems with the units. The Map is in Meter and I want as a result points per square Kilometer or points per Hectar!
- So what I have to do (What output cell size and so on)?

Thanks a lott!

Peter

Re: Best way to define search radius for Kernel density analysis

PeterMarkus1 — Tue, 12 Feb 2013 19:29:44 GMT

I want to display the density of house sells in a city, with a ruster surface. Input data are points - one point per sell.

So for this tool I have found tow video tutorials:
http://video.arcgis.com/watch/401/pe...nsity-analysis
(the hole video)
http://video.esri.com/watch/903/spat...best-practices
(only the first 16 min.)

So I have started with the fowolling steps:
1) Integrate (to summarize the points in a area)
2) Collect events (to get a count field)
3) Calculate Distance Band (as shown in the video spatial best-practices)
4) Calculate the "search radius" - one of the inputs for the density tool
- Load "Incremental Spatial Autocorrelation" toolbox (as shown in the video spatial best-practices)
- Values from Distance Band
Maximum Distance = Beginning Distance
Average Distance = Distance Increment