True-score-model correlations between term scores exceed 0.90 for almost all course-specific tests¶

Claim · All claims
Evidence · 2 studies · 2 associational r2 · q2 · i3 large
Currency · newest study 2022 · checked against its sources 2026-10-17 (automated, 2 of 2 entries) · not reviewed by a person · overdue for a recheck since 2025: tool and model accuracy changes quickly

Subclaims¶

q2 i? Pearson correlation coefficients computed from true score model estimates are above 0.90 for almost all tests, indicating strong correlations between fall, winter, and spring scores; these corrected coefficients are higher than those from observed scores. → Wei He 2022

q2 i3 Pearson correlations computed from true score model estimates are above 0.90 for almost all tests and are higher than observed-score correlations because they are corrected for attenuation. → Thum 2019

Evidence¶

Wei He 2022¶

Wei He. (2022). Achievement and Growth Norms for Course-Specific MAP® Growth™ Tests. NWEA Research Report. https://www.nwea.org/research/publication/achievement-and-growth-norms-for-course-specific-map-growth-tests/

q2 · i? · associational · r2

Correlational analysis reported in Section 3.3 and Table 3.2, comparing model-based correlations (corrected for attenuation) with observed-score correlations for each subject across fall–winter, fall–spring, and winter–spring pairs. The report notes the corrected coefficients "are therefore higher than those from the observed scores," e.g., Algebra 1 fall–winter r of 0.92 versus 0.85 observed.

"the Pearson correlation coefficients computed based on the estimates from the true score models are above 0.90 for almost all tests, suggesting that scores from each administration were strongly correlated"

Thum 2019¶

Thum, Y. M., & He, W. (2019). Achievement and growth norms for course-specific MAP® Growth™ Algebra 1, Geometry, and Algebra 2 tests. NWEA Research Report. Portland, OR: NWEA. https://www.nwea.org/research/publication/achievement-and-growth-norms-for-course-specific-map-growth-algebra-1-geometry-and-algebra-2-tests/

q2 · i3 · associational · r2

Correlational analysis of observed RIT scores and true score model estimates (Table 3.2) for Algebra 1, Geometry, and Algebra 2. Printed correlation coefficients (r) include r = 0.91 (Algebra 1 fall–winter, true score model) versus r = 0.86 observed, with model-based coefficients "above 0.90 for almost all tests" and corrected for attenuation.

"the Pearson correlation coefficients computed based on the estimates from the true score models are above 0.90 for almost all tests, suggesting that scores from each administration were strongly correlated"

Discussion¶

Related Claims¶

• The course-specific MAP Growth norms were built from 747,936 test events administered to 342,821 students in Grades 6–12 across 50 states between Fall 2017 and Spring 2019. — related
• Between-term score correlations are moderate and lowest for Phonological Awareness — reports the opposite
• Cross-term Foundational Skills scores were moderately correlated, with correlations ranging from 0.48 to 0.82 depending on domain and grade — reports the opposite
• Normality assumptions of the true score model appeared reasonable for the course-specific tests — related
• School effectiveness estimates from fall-to-spring versus spring-to-spring growth correlate only moderately to strongly (.399 to .705), below the .90 threshold at which rank orderings diverge in accountability — related