Only about half of misfit items were flagged in common by the AllYr and LatestYr samples, which the authors found surprising¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2019 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2022: tool and model accuracy changes quickly

Subclaims¶

q2 i? For Reading, 141 of 274 unique misfit items were common to both samples; for Mathematics, 159 of 350 were common. → He 2019

Evidence¶

He 2019¶

He, W. (2019). MAP Growth K–2 item fit analysis study. NWEA. https://www.nwea.org/research/publication/map-growth-k-2-item-fit-analysis-study/

q2 · i? · associational · r2

Cross-sample consistency analysis in Table 2.4 comparing items flagged in the AllYr versus LatestYr samples; the report notes that if samples were representative, "the same items are expected to be flagged by both samples."

"However, for both content areas, only about half of the misfit items were flagged as common in both samples. For Reading, 141 out of the 274 unique misfit items were common in both samples, whereas for Mathematics, 159 out of the 350 unique misfit items were common in both samples."

Discussion¶

Related Claims¶

• Item fit findings were the same regardless of whether the AllYr or LatestYr response sample was used — reports the opposite
• At least 97.5% of Reading items and 92.5% of Mathematics items passed the fit check, with 7 Reading and 23 Mathematics items flagged for misfit — related