Dually adaptive online IRT testing system with application to high-school mathematics testing case

Abstract

The item response theory (IRT) provides us not only the abilities of examinees but also the difficulties of items. Adaptive testing using the IRT selects the most appropriate items to examinees automatically, resulting in more accurate ability estimation and more efficient test procedures than the conventional testing. However, the item parameters remain constants even if the features of the examinees change. To overcome this situation, we use the dually adaptive online IRT testing system, where “dually adaptive” means that one is targeted to the adequate item selection and the other is targeted to the adjustment of the difficulty values for items. We have applied this method to the high-school mathematics testing case, and we have found that the system works well.