Data mining is known to have a potential for predicting user performance. However, there are few studies that explore its potential for predicting student behavior in a procedural training environment. This paper presents a collective student model, which is built from past student logs. These logs are first grouped into clusters. Then, an…

The author investigates how ability and gender affect grades on homework projects performed by assigned pairs of students in an undergraduate macroeconomics course. The assignment grade is found to depend on the ability of both students, and the relative importance of the stronger and weaker student differs in predictable ways depending on the…

This report was written to provide guidance in the development and evaluation of alternative instructional approaches that hold promise of improving instructional effectiveness. The main focus of the report is on how to identify and test interactive relationships between individual differences among learners and instructional conditions or…