thomas.nies_noaa

Getis Gi* - Problem with selected records

Discussion created by thomas.nies_noaa on Oct 1, 2011
Latest reply on Oct 4, 2011 by lrosenshein-esristaff
I am trying to analyze values in a spatial grid using the Getis Gi* hot spot tool. I started with point data for observed fishing tows, and each point has an amount caught. I aggregated the point data into the cells of the grid, summing the amounts caught in each cell. (For simplicity I have left out a few steps here). Because there aren't the same number of observations in each cell, I want to run the hot spot analysis several times, including only cells with a minimum number of two types observations in each run. I can easily query for the number of observations because I retained the counts for the two different types of observations.

The tool's help file says the tool will only run on selected features, so I tried selecting the cells I want using the select by attribues tool and using the definition query tool.  My selection is simple: it is of the form "counttype1>0 and counttype2>0". Neither approach works - my output includes cells that do not meet my minimum number of events criteria. I don't really want to create a new layer or feature for every number of observatiosn I want to try.

Any ideas what the problem might be?

Thank you for your help.

Note: I case it matters: the file I am analyzing is in a personal geodatabase; I am putting the output in a shape file. There are no null records.

Outcomes