Hi, I'm doing some research in which I have to apply some statistics. I've been scouring literature to try and find what I need, but have not been able to. I hope someone here might take pity and help me!
I have a test which I ran where the result was PASS or FAIL for each trial. I have calculated the probability of the number of passes I should get and want to compare it to the number of passes I actually got to see if the difference is significant. I tried applying the binomial test and that didn't seem to work (I got 0), and I've tried the chi-square test and that doesn't seem to work either as it appears you need more than one set.
The actual figures were:
461 successes from 2940 trials, where expected was 184 successes.
Any help to point me in the right direction would be very much appreciated.
Thanks for taking the time to reply. I've read up on what you sent, I think I might be misunderstanding it though. Does calculating the confidence interval not show (in very crude terms) that the results are reliable with 95% confidence? I suppose what I'm really asking is, is it possible with the type of results I have to calculate whether the difference between obtained results and expected results is significant?