Misclassified assessments cluster near placement cut scores¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2021 · checked against its sources 2026-10-28 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Of 285 misclassified assessments (GRU, α = 0.99), about 52% are within two items of a cut score and about 78% within five items. → Matayoshi 2021

Evidence¶

Matayoshi 2021¶

Matayoshi, J., Cosyn, E., & Uzun, H. (2021). Are We There Yet? Evaluating the Effectiveness of a Recurrent Neural Network-Based Stopping Algorithm for an Adaptive Assessment. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00240-8

q2 · i? · design · r2

Histogram analysis (Fig. 9) of the difference between item scores and nearest cut scores for the 285 assessments misclassified by the GRU model at α = 0.99. The article notes that when an item score is within a handful of items of a cut score, it is unclear which placement is truly appropriate.

"149 of these misclassified assessments (about 52%) are within two items of a cut score, and 222 assessments (about 78%) are within five items of a cut score"

Discussion¶

Related Claims¶

• Feeding ALEKS assessment state to an RNN classifier yields a large boost in placement accuracy over the assessment alone at early stopping points — related
• Cut scores for transfer-level mathematics placement vary considerably across California community colleges, sending mixed signals about college readiness — related
• Passing the college algebra placement test near the cut-off and enrolling in dual enrollment college algebra was associated with a 16 percent higher likelihood of going to college — related
• Dual enrollment college algebra near the cut-off was associated with a 23 percent higher likelihood of earning a college degree — related