A Cross-Validation of easyCBM Mathematics Cut Scores in Washington State: 2009-2010 Test. Technical Report #1105.

In this technical report, we document the results of a cross-validation study designed to identify optimal cut-scores for the use of the easyCBM mathematics test in Oregon. A large sample, randomly split into two groups of roughly equal size, was used for this study. Students’ performance classification on the Oregon state test was used as the criterion. Optimal cut scores were examined for each group. Results indicate quite stable cut scores across 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 of the validity of the cut scores as optimal to predict student performance on the Oregon statewide large-scale assessment. Cross Validation: Oregon 1 In this technical report, we present the results of a cross-validation study examining the diagnostic efficiency of easyCBM. Anderson, Alonzo, and Tindal (2010) used a large sample in Oregon to established optimal cut scores for predicting state test performance classification (not passing/passing). The current study extends the Anderson, Alonzo, and Tindal results by randomly separating the same sample into two groups and examining the optimal cut points on easyCBM for each group. The stability of the optimal cut points across the randomly selected groups provides evidence to support the specified cut points for predicting state test classification