1

I have a point feature class. All points are the same, it's not weighted.

I want to use Spatial Autocorrelation (Morans I) tool but it only takes a field for weight. I tried fooling it by adding a field with the value 1 for all points but it comes back with an error.

How can I use Moran I in ArcGIS on a point feature class?

5

You cannot use the Moran's I on an unmarked process. The values, at each location, are what the statistic is based on and therefore cannot be absent or uniform.

Your only real option, in ArcGIS, for evaluating the spatial process (dispersion/clustering) of an unmarked point process is the Nearest Neighbor Index (Average Nearest Neighbor Tool).

  • what about aggregating the points into polygons like they do for the census? – Rudolf O Apr 14 '16 at 17:52
  • 1
    This will introduce a notable MAUP issue and seriously bias/change the autocorrelation and autocovariance structure of the data. The classic example of aggregation bias due to MAUP, is actually in the census data. And, please do not use ESRI's ridiculous collect events tool as it will introduce an even more arbitrary bias. The the case of MAUP, autocorrelation is not supported and is likely just a result of the aggregation scheme. – Jeffrey Evans Apr 14 '16 at 18:11

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.