Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Firstly, thanks for answering my last question. I appreciate the help and effort put in.

I have another question to put forth. Again, it is related to Medical Statistics.

There are one third of male prisoners who have a history of heroin injection. One in 200 of them will die from heroin overdose. To prevent plausibly 30% of these deaths, a major trial will randomise individuals to control and intervention.

And we need to calculate how many consented prisoners need to be randomised for the proposed trial to have 80% power to discern a 30% reduction in heroin overdoses within 4 weeks of release for prisoners.

What I have been taught is to do something like this:

Target reduction is 30%. Initial ratio to start with is 0.5% and have to go to 0.35%.

So, (0.5*99.5)+(0.35*99.65) and divide this by 30^2 to get the value of 'n', i.e., the number in each group that should be taken to conduct the test.

The value of n is coming out to be 0.009 something, which I think is wrong. Am I reading the question wrong? How else can I do this question?

Thank you very much again!

share|cite|improve this question

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.