Predictive Accuracy of a Proficiency Cut Score in a Benchmark Assessment for a State Assessment

• In Event: Assessment, Achievement, Accountability, and Outcomes

Abstract

A researcher evaluated the accuracy of a proficiency cut score in the benchmark assessment to predict students’ proficiency status in the subsequent state assessment. Using students’ test scores in a school district, the researcher assessed whether reaching a proficiency level in the benchmark assessment had a causal impact on increasing the probability of reaching a proficiency level in the state assessment. Finding no causal impact of the cut score, the researcher alternatively applied a precision-recall curve to find an optimal proficiency cut score that maximizes the accuracy and minimizes the inaccuracy in predicting the proficiency level in the state assessment. Based on the results, the researcher suggests some potential approaches to increase the predictive accuracy of the cut score.

Author

• Takeshi Terada, Washington University in St. Louis