Spatial Autocorrelation

[sarahvoeller]

I have samples of individuals from various areas in South and Central America (12 samples, so 12 locations).  Each sample has a different number of individuals with a measurement assigned to them.  Each sample also has somewhere between 4-40 individuals.  So there are coincident data at each location.   

I would like to see if there is spatial autocorrelation (clustering/dispersion) among the samples taking into account this measurement.  I am using the Spatial Autocorrelation Moran's 1 tool.  Having done something similar to this before, I felt each location could only have one value.  In the past (using geostatistical analyst), it would just average the values at each location.  So I went ahead and did that myself.  Thus I had 12 locations, each with one data point.  I ran the spatial autocorrelation tool, and there was nothing significant.   

I am doing it again without averaging the samples.  Thus each location as between 4-40 data points.  After running the tool again, it finds significant clustering.  However, if there are 12 locations with a ton of data points, I feel this is due to sampleing bias.  Is that right? 

Any suggestions on the best way to do this?

[DanPatterson_Retired]

from the help Spatial Autocorrelation (Global Moran's I)—Help | ArcGIS for Desktop

this Optimized Hot Spot Analysis—Help | ArcGIS for Desktop would be worth looking at as well,

Since you have multiple people ascribed to a polygon, one does have to consider how applicable the polygon boundaries are

[sarahvoeller]

It is actually point data.  I read each observation in with a lat and long coord.  So there is a couple points on top of eachother in each of the 12 locations.  There are a total of 255 points.  I suppose the hotspot analysis would idenfity clusters if there were any.  I will give that a try and see what results suggest.