The purpose of this study was to compare different statistical and methodological approaches to standard setting and determining cut scores using R-CBM and performance on high-stakes tests. One thousand seven hundred and sixty-six-students were followed longitudinally from first through third grades using R-CBM benchmark assessment. In addition, students were administered the Minnesota Comprehensive Assessment (MCA) at the end of third grade. Predictive validity and diagnostic accuracy analyses using discriminative analysis, logistic regression, and receiver operator characteristic (ROC) curves were conducted. Results suggested that R-CBM is strongly associated with MCA performance at each grade level and is both accurate and efficient in predicting those students who are likely to pass the reading portion of the MCA beginning in first grade. Applied and theoretical implications are discussed along with future research.
Stored only when both papers are in the corpus — 184 citations exist upstream.
Imported from OpenAlex (CC0) — nothing here is generated.