Bayesian Networks in Educational Testing

In this paper we discuss applications of Bayesian networks to educational testing. Namely, we deal with the diagnosis of person’s skills. We show that when modeling dependence between skills we can get faster a better diagnosis. We also show that there exist test setups for which it is impossible to get a complete and correct diagnosis unless we model dependence between skills. We present results of experiments with basic operations with fractions. The experiments suggest that the test design can benefit from a Bayesian network modeling relations between skills not only in the case of an adaptive test but also when designing a fixed (non-adaptive) test.