[Oneday]

Hi, I was reading through the grading explanation by AICPA and this paragraph caught my attention.

“14. What do you mean when you say “statistical characteristics” of test

questions?

There are three statistics used to describe the questions: Difficulty – whether the

question is generally easier or more difficult for candidates, Discrimination – how well the

question differentiates between more able and less able candidates, and Guessing – the

chances of candidates answering the question correctly just by guessing. The statistics

are generated when the questions are administered as pretest questions and used in the

scoring when the questions are operational. The formulas for generating the statistics

and scoring the Exam come from a scoring approach commonly referred to as ―Item

Response Theory.‖ Item Response Theory is currently being used or has recently been

adopted by nearly all of the large licensing examination programs in this country and

also by many of the moderate-sized and smaller examination programs. “

Three important elements here are: Difficulty (to candidate), Discrimination (of more able candidate), and detection of guessing.

After reading this, I thought to myself, how can they detect all these elements with only input of answering MCQ questions?

Few things that I could think of them using are: Time taken, Flags, Repeated viewing of past questions and scratch paper.

Do you guys think that if you finish each questions faster, you’d get better score?

Do you guys think that if you flag less you’d get better score?

Do you guys think that if you don’t go back to review unsure questions,you’d get better score?

What do you guys think?