0
$\begingroup$

Apologies if this is ridiculously basic - I have searched the site but my vocabulary is probably too limited to be successful.

I have a group of individuals performing a task with a boolean outcome - success or failure. Each individual performs the task a different number of times.

I'm asked to report on the success rate of individuals, but my intuition is that I should be able to identify a confidence interval, especially since some individuals have performed the task many fewer times than others.

Some concrete numbers, since I'm probably being unclear:

Overall there have been 688 attempts with 175 successes, a 25.4% success rate.

Individual 1 has made 112 attempts with 31 successes, a 27.7% rate. Individual 2 has made 14 attempts with 3 successes, a 21.4% rate.

It seems obvious to me that I'm much less confident in the true success rate for Individual 2 than I am Individual 1, but I don't know how to measure that, or even what the name of this kind of task is (repeated binary? something like that?)

Thanks for any advice!

$\endgroup$
0
$\begingroup$

I think this should help: https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval

The very first equation should be roughly what you need,

$\endgroup$

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.