comparing two groups with binary data


Suppose I am testing two drugs, I and II. The response profile is either I >II, II<I or I == I. I was trying to figure out the best way to do this.

One way I thought of was to throw out all the ties (I == II), and then assign a 1 where I>I and a 0 I<II. Then this boils down to a binomial distribution (which I can approximate with the normal).

But I was wondering if throwing away the ties is really appropriate... If I don't throw away ties, I can't use the binomial distribution (so would I switch to some multinomial test)?

The other thing I can think of is some wilcoxon rank sum test or mann whitney u test with ties... but I was wondering if anyone else has an idea? The concern here is that there will be a LOT of ties...

Last edited:
Hi greeniguana,

could you be more specific about the research question and design? Are the scores independent or dependent? This will be important for the appropriate test. If the scores are dependent you could use a Wilcoxon signed rank test which will exclude all ties. In the other scenario you could use a Mann-Whitney but I don't have in mind how it will treat ties.



Omega Contributor
Yes, please describe the formatting of variables in detail and your hypothesis. Are both drugs used on the same person or are there two groups, are you wanting to test the non-inferiority, inferiority??