Kybernetika 40 no. 3, 333-348, 2004

Building adaptive tests using Bayesian networks

Jiří Vomlel

Abstract:

We propose a framework for building decision strategies using Bayesian network models and discuss its application to adaptive testing. Dynamic programming and $AO^{\star}$ algorithm are used to find optimal adaptive tests. The proposed $AO^{\star}$ algorithm is based on a new admissible heuristic function.