I gave a 12 item true-false quiz (which I created) to my 19 students.

I noticed that some questions were very obviously easier than others, so I decided to run an item analysis. By looking at the item difficulty results, it does seem like that's the case. I am thinking of re-administering the quiz and excluding items with item difficulty below 0.5.

But with such a small sample size, should I even bother with item analysis?


With this sample size (and number of items/questions), any statistical analysis would be questionable. However, from a purely descriptive perspective, the item analysis might suggest which are the easiest and the hardest. It probably would not let you do any more refined ranking of the item-difficulty.

| cite | improve this answer | |

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.