Previously, I had a question about CI for Patient-Years (py) and there was a great answer from @TamasFerenci. Now I need to find out the $p$ value for the py of two different groups.
I have a table which contains events per 1,000 py:
Group A Group B Hospitalization/1,000 py 8.8 38.0 Death/1,000 py 18.0 36.6 ... ... ...
There is already a question about significance test for two poisson distributions but I am not sure how this applies on py, because in case of py we have rates and not the original data (observed number of events and observed follow-up time). Can I we estimate whether the two rates are significantly different using
poisson.test(x= 38, T= 1000, r= 8.8)$p.value for hospitalization? Or do I need the original data with observed number of events and observed follow-up time?