Sakumura, Takenori - Chuo University ( Presenting )
Hirose, Hideo - Hiroshima Institute of Technology
A Bias Reduction Method for Ability Estimates in Adaptive Online IRT Testing Systems
To evaluate the ability of examinees, the item response theory (IRT) gives us an useful information. The IRT evaluates the examinee’s ability and provides the item characteristics. Recently, we have configured the adaptive online testing using the IRT as one of the CBT (Computer Based Testing) methods, thereby we have been able to obtain the examinee’s ability rating in short testing time. However, when the number of items is too small, we observed biases of estimates for the ability parameter. In this study, we have performed simulation studies under various conditions, and have found the magnitude of such biases. In addition, to circumvent the biases due to the Bayes procedure, we have proposed a simple method to reduce the biases.
item response theory, adaptive test, item selection, item bank, ability estimate, bias
International Journal of Smart Computing and Artificial Intelligence, International Institute of Applied Informatics, Volume 1, Nomber 1, Pages 59--72, 2017