EPFA estimates fewer trials to mastery for above-average students and more trials for below-average students relative to standard PFA¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In the KDD dataset, the average better-performing student was estimated to need 2.7 fewer trials to mastery per KC under EPFA, while the average lower-performing student was estimated to need 2.2 more trials. → Eglington 2022

Evidence¶

Eglington 2022¶

Eglington, L.G., Pavlik, P.I. (2022). How to Optimize Student Learning Using Student Models That Adapt Rapidly to Individual Differences. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-022-00296-0

q2 · i? · design · r2

Post-hoc analysis comparing PFA and EPFA estimated trials to mastery (correctness probability >= .95) per student per dataset, partitioning students above versus below average. Directional difference reported descriptively; no test statistic or effect size printed.

"the average better-performing student in the KDD dataset was estimated to need 2.7 fewer trials to mastery per KC on average, and the average lower-performing student was estimated to need 2.2 more trials to achieve mastery per KC on average."

Discussion¶

Related Claims¶

• Adding a Prior Error Valence (PEV) feature to a population-parameter model reduces systematic mastery-timing error in simulation — related
• Learner models with population-level parameters systematically misestimate the trial of mastery for most students whose learning rates vary — related