A theoretical formalization of the probability of solving multiple-choice tests and its application to different scoring rules
In multiple-choice tests, guessing is a source of test error which can be suppressed if its expected score is made negative by either penalizing wrong answers or rewarding expressions of partial knowledge. We consider an arbitrarymultiple-choice test taken by a rational test-taker that knows an arbitrary fraction of its keys and distractors. For this model, we compare the relation between the obtained score for standard marking (where guessing is not penalized), marking where guessing is suppressed either by expensive score penalties for incorrect answers or by marking schemes that reward partial knowledge. While the “best” scoring system (in the sense that latent ability and test score are linearly related) will depend on the underlying ability distribution, we find a superiority of the scoring rule of Zapechelnyuk (Economics Letters, 132, 2015) but, except for item-level discrimination among test-takers, a single penalty for wrong answers seems to yield just as good or better results as more intricate schemes with partial credit.