Students encountered substantial numbers of items with changed parameter estimates, averaging 11–38% of test length by subject¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2025: tool and model accuracy changes quickly

Subclaims¶

q2 i? Across terms, the average number of items with changed difficulty estimates encountered per test ranged between 9 and 19 for math, 5 and 11 for reading, 6 and 10 for language usage, and 3 and 8 for science, equivalent to 11–38% of test length. → He 2022

Evidence¶

He 2022¶

He, W. (2022). MAP Growth item parameter drift study. NWEA Research Report. https://www.nwea.org/research/publication/map-growth-item-parameter-drift-study/

q2 · i? · associational · r2

Descriptive statistics from the rescoring analysis (Table 3.3) reporting how many items with new parameter estimates each rescored adaptive test contained. The minimum was as low as 1, and the maximum for Spring 2013 math was 36, just 15 items short of the full-length test.

"the average number of items with difficulty estimates different from their original ones ranged between 9 and 19 for math, 5 and 11 for reading, 6 and 10 for language usage, and 3 and 8 for science, equivalent to 18~38% for math, 13~27% for reading, 13~20% for language usage, and 11~25% for science"

Discussion¶

Related Claims¶

• Rescoring with new item parameters changed average ability estimates negligibly, with new and original scores correlated above 0.99 — related
• Average drift in MAP Growth item difficulty estimates is negligible across subjects, with original-new correlations above 0.99 — related
• Both item-level and test-level analyses indicate the MAP Growth measurement scales are remaining stable — related