Publications & Resources
A Bayesian Network Approach to Modeling Learning Progressions and Task Performance
Patti West, Daisy Wise Rutstein, Robert J. Mislevy, Junhui Liu, Younyoung Choi, Roy Levy, Aaron Crawford, Kristen E. DiCerbo, Kristina Chappel, and John T. Behrens
A major issue in the study of learning progressions (LPs) is linking student performance on assessment tasks to the progressions. This report describes the challenges faced in making this linkage using Bayesian networks to model LPs in the field of computer networking. The ideas are illustrated with exemplar Bayesian networks built on Cisco Networking Academy LPs and tasks designed to obtain evidence in their terms. We briefly discuss challenges in the development of LPs, and then move to challenges with the implementation of Bayesian networks, including selection of the method, issues of model fit and confirmation, and grainsize. We conclude with a discussion of the challenges we face in ongoing work.
West, P., Rutstein, D. W., Mislevy, R. J., Liu, J., Choi, Y., Levy, R., … Behrens, J. T. (2010). A Bayesian network approach to modeling learning progressions and task performance (CRESST Report 776). Los Angeles: University of California, Los Angeles, National Center for Research on Evaluation, Standards, and Student Testing (CRESST).