Several questions about Moran's I

[MaryZylo]

(1)  I got this error when running Moran's I:


Executing: SpatialAutocorrelation Intersects\Eagle_Winter_Day_NAD83_Intersect_Crown_Bulk_Density cbd_fin false "Inverse Distance" "Euclidean Distance" None # # 0 0 0


Start Time: Thu Aug 04 08:29:03 2011


Running script SpatialAutocorrelation...


ERROR


000641: Too few records for analysis. This tool requires at least 3 feature(s) to compute results.


<class 'ErrorUtils.ScriptError'>: Exiting....


Failed to execute (SpatialAutocorrelation).


End Time: Thu Aug 04 08:29:09 2011 (Elapsed Time: 6.00 seconds)

There are 2679 records and more than three values for cdb_fin, so I don't understand the error message.



(2) This tool also doesn't seem to recognize raster layers.  Does anyone know of a tool that looks at spatial autocorrelation for raster layers?

(3)  I would think that the layers I'm using for covariates (crown cover, veg type, stand density index, etc) would be spatially autocorrelated.  Is there a way that I can do my analysis to allow for that?

[LaurenRosenshein]

Hi Mary,

I'm sorry you're having trouble running Spatial Autocorrelation.  There are some possibilities for why you're seeing this error.  One possibility is that you may have a selection set?  If you have any features selected the tool will honor that selection, so make sure you clear any selection before you run the tool (unless, of course, you specifically want to analyze that selection set).  Another possibility is either null values or invalid geometry.  Both of these could also be causing trouble.  For the invalid geometry, you may want to try running the Repair Geometry tool and see if that helps.  If none of this helps, you can send over your data and we can see if we can reproduce the issue here.

Your next question is about recognizing raster layers.  The best thing to do is to convert your rasters to points, at which point you can use the Spatial Autocorrelation tool.  To the best of my knowledge there is no tool in ArcGIS that calculates spatial autocorrelation statistics for rasters. 

As far as your last question goes, I'm not 100% sure what you're trying to do, but it sounds like you may want to do a regression analysis, in which case you could use Ordinary Least Squares Regression (for which you will need point data and can do a raster to point conversion).  You can learn a lot more about regression analysis in ArcGIS, and the assumptions of OLS in general, from this one hour free training seminar called Regression Analysis Basics.

[MaryZylo]

I have version 9.3.1 at home.  I was on campus last week and tried running the same Moran's I calculation in ArcGIS version 10 on one of the layers.  It worked, but I was out of time, so didn't try the rest.  I don't know what is different, but I'll try the rest of the layers while I'm back on campus next week.

Thanks for your reply.