Adding PEV or student-level proportional correctness significantly reduces the absolute value of student-level signed error in all six datasets¶

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? Paired comparisons within students showed that adding PEV to PFAP or student-level proportional correctness to RKCPFA reduced absolute error relative to the base models in all six datasets (ts > 6.57, ps < .0001). → 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

Paired t-tests comparing student-level absolute error values across models within each of the six datasets. The article reports reduction "in all six of the datasets we evaluated" with ts > 6.57, ps < .0001; no effect size printed.

"Adding PEV to PFAP (i.e., EPFA) or student -level proportion al correctness to R KCPFA reduced absolute value of error relative to RKCPFA or PFAP in all six of the datasets we evaluated, ts > 6.57, ps < .0001."

Discussion¶

Related Claims¶

• Learner models with individual-difference features (PEV, student-level proportional correctness) improve cross-validated fit on six educational datasets — a broader claim this one bears on
• Adding a Prior Error Valence (PEV) feature to a population-parameter model reduces systematic mastery-timing error in simulation — related
• The combined model with both PEV and student-level proportional decay typically fit better than either feature alone — related