SERDA-derived scores classify children into DMT and AVI proficiency classes with moderate to good accuracy and items discriminate moderately well or better¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Ordinal regression predicting DMT proficiency classes reached weighted kappa 0.65 and average F1 0.70; AVI prediction reached weighted kappa 0.73 and average F1 0.77. → van der Velde 2025

Evidence¶

van der Velde 2025¶

van der Velde, M., Harmsen, W., Veldkamp, B. P., Feskens, R., Keuning, J., & Swart, N. (2025). Speech Enabled Reading Fluency Assessment: a Validation Study. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00480-y

q2 · i? · design · r2

Decision-making inference: ordinal regression models predicting DMT and AVI proficiency classes from LNIRT ability and speed estimates, person-level WCPM scores and Grade. The AVI model showed "a weighted kappa of 0.73 and an average F1 score of 0.77".

"The ordinal regression model used to predict the DMT proficiency classes showed a weighted kappa of 0.65 and an average F1 score of 0.70, indicating moderate to good classification accuracy."

Discussion¶

Related Claims¶

• SERDA oral reading metrics correlate with DMT and AVI classifications (0.32–0.88), with speed and WCPM metrics outperforming ability estimates — related
• MAP Reading Fluency SWCPM scores classify students into ARM proficiency categories with exact match rates of 74.6–90.8%, kappa 0.60–0.85, and overall accuracy 0.81–0.96 — related