Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
I am facing a problem regarding sample size calculation of clinical trial.
Currently a drug is used at
2.5mg for adult and1.5mg for children and death rate is0. Now we want to reduce the drug level to1.0mg for adult and0.5mg for children.
If I want to keep the death rate at same for new drug level then how many sample should we take to justify.
You have a more difficult problem than it seems that you realize. There is not a single answer to this problem - you are describing a non-inferiority trial. You can't "prove" that the death rate stays at zero because you will have a confidence interval for a proportion, whose width depends on how much data exist to support your statement that the death rate is zero.
Here is a place to begin on reading about non-inferiority trials: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC59590
Unfortunately for you, non-inferiority trials often require much larger sample sizes than conventional superiority trials. Good luck!
