0
$\begingroup$

I am trying to compare two groups - test, control. Each group has ~15,000 participants. Each participant either completed or did not.

I can look at the completion rate between the two groups, it would be this:

# completed / # in group

How can I come up with confidence intervals for the completion rate? What is the best way to accomplish that in r?

$\endgroup$
1
$\begingroup$

-- Please check the formula for confidence intervals (CI) of the binomial distribution. You can calculate CIs for each group and compare them. If the intervals do not overlap then the groups are different. See https://en.wikipedia.org/wiki/Binomial_distribution -- You can also use the normal approximation of the binomial distribution and use the normal distribution for comparing the means of each group. You have a rather large sample size so the normal approximation is OK to use. Hope this helps.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.