Equated WCPM scores from non-reference passages show smaller residuals against reference-passage scores than raw scores, with one passage exception¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2020 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2023: tool and model accuracy changes quickly

Subclaims¶

q2 i? Mean residual sum of squares between scores on the final reference passage and scores from a non-reference passage are smaller for equated than raw WCPM scores for 21 of 22 passages, with Passage WGK_11001 the exception. → Chen 2020

Evidence¶

Chen 2020¶

Chen, J., & Simpson, M. A. (2020). Equating words-correct-per-minute (WCPM) scores across passages of MAP Reading Fluency. Portland, OR: NWEA. https://www.nwea.org/research/publication/equating-words-correct-per-minute-wcpm-scores-across-passages-of-map-reading-fluency/

q2 · i? · design · r2

Residual analysis limited to the 22 passages administered together with the final reference passage FG1_10006 (Table 3.3; e.g., FG3_10008, N 16,990, raw 189.98 versus equated 132.26). One exception, "except for Passage WGK_11001," where raw residual was smaller (157.89 versus 161.50).

"Compared to the raw WCPM scores, the equated WCPM scores had smaller mean residual sum of squares except for Passage WGK_11001, indicating that the equated scores are much closer to students’ actual scores on the reference passage."

Discussion¶

Related Claims¶

• Cross-term WCPM score differences are more consistent across passage positions after equating, supporting progress monitoring — related
• Equated WCPM scores are more highly correlated across passages read by the same student than raw WCPM scores, suggesting greater reliability — related
• Equated WCPM scores generally correlate more highly with MAP Growth Reading RIT scores than raw WCPM scores, with one exception — related
• Equated WCPM scores show much less within-student variance than raw WCPM scores, indicating reduced passage-difficulty fluctuations — related
• Linear regression outperformed equipercentile and mean-sigma equating for predicting ARM scores and was selected as the final linking model — related