For example, each Census Tract has two categorical variables derived from two different methods. I'd like to figure out how similar those two methods are.

The software I will be using is R.

I have tried looking up answers online, but they do not quite answer my question. The answers online either involve auto-correlation of one variable or testing of spatial correlation between two continuous variables.

closed as unclear what you're asking by Spacedman, ahmadhanb, mgri, BERA, whyzar Jul 13 '17 at 8:39

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • This is the sort of question that requires a half-hour tutorial session with a stats tutor. Do the two categorical variables have the same set of categories? Then could you model if the two categories for a census area agree or differ, in which case you are left with a binary (binomial) model. Then there's the question of what's the model behind all this. Have you tried writing down a model for the joint distribution of categorical responses, given the data? – Spacedman Jul 13 '17 at 7:04

Browse other questions tagged or ask your own question.