Using student models to generate feedback in a university course on statistical sampling

Due to the complexity of the topic and a lack of individual guidance, introductory statistics courses at university are often challenging. Automated feedback might help to address this issue. In this study, we explore the use of student models to provide feedback. The research question is how student models can be used to generate feedback to university freshman in an online course on statistical sampling. An online activity was designed and delivered to 40 Biology freshmen. Instruments for generating student models were designed and student models were generated. Four students were interviewed about the generated models, and about the differences with their own estimation of their understanding. Results show that it is possible to generate individual feedback from student work in an online learning activity and suggest that discussing differences between own estimations and generated student models can be a fruitful teaching strategy.