Applying three models of learning to individual student log data

Normally, when considering a model of learning, one com-pares the model to some measure of learning that has been aggregated over students. What happens if one is interested in individual differences? For instance, different students may have received different help, or may have behaved dif-ferently. In that case, one is interested in comparing the model to the individual learner. In this study, we investi-gate three models of learning and compare them to student log data with the goal of seeing which model best describes individual student learning of a particular skill. The log data is from students who used the Andes intelligent tutor system for an entire semester of introductory physics. We discover that, in this context, the ”best fitting model ” is not necessarily the ”correct model ” in the usual sense