Growth-score differences between CBE and COLO are small, exceeding 0.2 only in Reading Grades K–1 (favoring CBE) and Mathematics Grade 8 (favoring COLO)¶

Claim · All claims
Evidence · 1 study · causal r2 · q2 · i1 small
Currency · newest study 2020 · checked against its sources 2026-10-09 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i1 Hedges' g effect sizes for winter-minus-fall RIT growth between engines exceed 0.2 in absolute value only for Reading Grades K and 1 (CBE higher) and Mathematics Grade 8 (COLO higher), all small by Cohen's guidelines. → Bo 2020

Evidence¶

Bo 2020¶

Bo, E., & Meyer, P. (2020). Comparability of MAP Growth tests administered through different technology and psychometric infrastructure: An engine evaluation study based on empirical data. Portland, OR: NWEA. https://www.nwea.org/research/publication/comparability-of-map-growth-tests-administered-through-different-technology-and-psychometric-infrastructure-an-engine-evaluation-study-based-on-empirical-data/

q2 · i1 · causal · r2

Descriptive effect-size analysis of Fall 2019 and Winter 2020 MAP Growth RIT records from 171,093 Nebraska students in 803 schools, comparing matched CBE and COLO school groups. Growth scores were computed as winter minus fall RIT; the article reports "the Altair effects are small according to Cohen’s guidelines" in the three grades noted.

"As shown in the last column, only Grades K–1 have the absolute effect size values above 0.2 in Reading. In Mathematics, only Grade 8 has the absolute effect size value above 0.2. In all three cases (i.e., Reading Grade K, Reading Grade 1, and Mathematics Grade 8), the Altair effects are small according to Cohen’s guidelines."

Discussion¶

Related Claims¶

• The Altair (engine) main effect is not significant for winter RIT scores in either content area, but an Altair-by-sex interaction is significant in Reading only — related
• Marginal reliabilities of MAP Growth winter scores are comparable across engines and all in the 0.90s, with CBE showing slightly higher precision (lower SEM) — related
• Test lengths are comparable across engines, but CBE test durations are higher than COLO's in both terms and content areas, more prominently in Reading — related
• The CBE and COLO engines met content specifications and recovered true scores well for the nine simulated MAP Growth tests — related
• Adaptivity and score reliability of both engines depend on item-pool depth; the CBE often performed better than COLO for extreme low or high achievers when item banks were shallow — related