I have some patients that have none, mild and moderate form of a disease monitored at baseline and at 6-months. I would like to do the mcNemar-bowker test to see whether the drug given to everyone has affected the severity of the disease (3 categories- none, mild and moderate), but the matrix looks upper triangular at the moment, since you cannot regress i.e go from mild to none, moderate to mild or moderate to none. The primary interest is to see if patients have remained (i.e. stabilized) or gotten worse after treatment. Is the mcNemar-bowker test an appropriate test here? If not, what would be an appropriate test? Thank you


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.