I have a dataset that lists a large number of binary variables for each member of the populations. It basically looks like this:
Patient_Number Measure_1 Measure_2 Measure_3 ...
0001 Yes No Yes
0002 No No Yes ...
0003 Yes Yes Yes ...
I want to assess which measures co-occur and to what extent. I am also interested to know if there are any combinations of measures that tend not to co-occur.
I am familiar with the R programming language but I do not know what an appropriate measure for this would be. My dataset is composed of ~400 patients and ~500 Measures but if I need to I can trim those down to subsets as small as 30 patients and 10 Measures.