Cross-Validation of easyCBM Reading Cut Scores in Oregon: 2009-2010. Technical Report #1108.

This technical report presents results from a cross-validation study designed to identify optimal cut scores when using easyCBM reading tests in Oregon. The cross-validation study analyzes data from the 2009-2010 academic year for easyCBM reading measures. A sample of approximately 2,000 students per grade, randomly split into two groups of roughly the same size, was used for this study. Students state test performance classification (passing/not passing) on the Oregon Assessment of Knowledge and Skills (OAKS) was used as the criterion. Optimal cut scores were identified for each of the randomly split groups with a receiver operating characteristic curve (ROC) analysis. Results indicated reasonably stable cut scores between groups. Further, the overall area under the ROC curve (AUC) was not statistically different between groups for any measurement occasion at any grade, providing strong evidence for the validity of identified cut scores as optimal to predict student performance classification on the Oregon state large-scale assessment. Cross Validation: Oregon p. 1 A Cross-validation of easyCBM Reading Cut Scores in Oregon: 2009-2010 In this technical report, we present findings from a cross-validation study examining the diagnostic efficiency of easyCBM® reading tests. Data for these tests were analyzed for grades 3-8, and came from the 2009-2010 academic year. Park, Anderson, Irvin, Alonzo, and Tindal (2011) used a large sample in Oregon to establish optimal cut scores for predicting performance classification (not passing/passing) on the reading portion of the Oregon Assessment of Knowledge and Skills (OAKS), the state test used in Oregon. We extend their study by randomly splitting the same sample into two groups and examining the stability of the optimal cut scores for each easyCBM® reading measure across the randomly selected groups. The relative stability of the cut points provides further evidence to support the specified cut point for predicting state test classification in Oregon. Theoretical Framework The online easyCBM progress monitoring assessment system was launched in September 2006 as part of a Model Demonstration Center on Progress Monitoring funded by the Office of Special Education Programs (OSEP). Since 2006, up to 17 forms for each reading measure have been developed for grades K-8. These reading measures accompany the 33 test forms available at each of grades K-8 for mathematics, together making up the easyCBM online