Abstract
Information technology is applied to many tasks in educational engineering. E-testing is one of important tasks in educational engineering. There are many previous studies on e-testing. An error rate in e-testing represents the probability of an event that an e-testing method computes wrong evaluations for understanding of students. In previous studies the error rate is not minimized theoretically. We propose an e-testing method based on statistical decision theory. The proposed method minimizes the error rate with respect to the Bayes criterion. Dynamic programming technique is used to solve the e-testing problem. We show the effectiveness of the proposed method by some numerical calculation examples. The proposed method is one of adaptive tests of hypotheses in statistics. The proposed method can be applied to many tasks in healthcare industry.
