Sample size calculation to detect mortality benefit of treatment

Hi folks,

I was wondering if you could help me with this. I thought I'd be able to work this out but my stats knowledge is very jaded now.

If the mortality rate from an illness is 2% and I want to conduct a trial comparing treatment X with placebo, with a view to finding out whether treatment X reduces mortality from that illness--- how do I determine what sample size I will need to be able to say whether or not treatment X has a mortality benefit.

Thanks in advance.


Less is more. Stay pure. Stay poor.
Mortality is collected at a standardized time, say 5-years, and you are not trying to control for time to event?
Mortality will be collected at day 14 and 30 from the day of diagnosis, which is almost always the day of initiation of treatment in my context.

Not sure of the relevance of controlling for "time to event". Seems like I've forgotten the little stats that I used to know.