I have a data set in which survey stations, each with a unique ID, have a series of attributes. Each station has the counts for many different species found at that lat/long coordinate. I want to look at associations between the different species (how often do scallops and sand dollars occur together? Are they more likely to be found together than, say, scallops and hermit crabs?). And it would be great to weigh the relative overlap- if one species occurs at every station, it's not as important to note overlap as ones that only occur together. These are all saved as separate layer files selected from the original data set, and I have also converted them to raster files, but I don't know which tool to use to get the results I want. I'm more interested in presence/absence than the total count at each station. I just want to know which of the species occur together, but since they're counts that are all attributes of the survey stations, I'm not sure how to proceed. Grouping analysis seemed likely but I don't think the structure of the data is right for it.
Example of attribute table for survey stations
Station 1:
41.14182525 -71.423448
scallops 2
sea stars 5
crabs 0
hermit crabs: 0
anemones: 0
sand dollars: 1
and so on.
