I'd like to know how to calculate the following. Given M proportions for a sample of N multiple-choice question correct answer choices, where each of the questions has M answer choices 1st to Mth, what is the probability that the M proportions deviation from 1/M would be seen by chance?

I hope I've stated my question correctly. Example: Given a set of correct answers for N=500 questions each with M=5 answer choices A to E as follows: A 0.223, B 0.191, C 0.196, D 0.185, E 0.205; what is the probability that those results will be observed by chance? Or conversely, what is the probability that the test producer's choices of assignments of correct answers to letters A to E was biased?

(I have access to RStudio but it's been a long time since my minimal use of R.)


Your Answer

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

Browse other questions tagged or ask your own question.