Paired analysis/ Stuart-Maxwell test

#1
Hi everyone,

I am performing a paired analysis, cases paired with controls, with each individual having a status of current,former or never. I initially performed the Stuart-Maxwell test to determine if there was a significant difference between the proportions of possible paired statuses (1st attachment).

Firstly I was curious if this was a suitable test to perform.

Secondly, I am now curious whether there is a significant difference between the combination of pairs that have "opposite combinations. I've highlighted what I mean by opposite pairs in the second attachment. Ideally, these would balance each other out, but given this is not the case I need to know if there is a significant difference between them as this could have an effect on the data I am looking at.

thanks,
A
 
Last edited: