Abstract: Currently, 49 states in the U.S. measure student achievement growth as part of their statewide elementary and secondary school student-testing programs and for accountability for districts, schools, or educators. These systems use the average of individual students’ growth for all the students in a district, school, or educator’s class. Averaging growth measures for schools, districts or educators with few students can result in substantial year-to-year fluctuations. We proposed smoothing the aggregate growth measures across time using the Empirical Best Linear Prediction (EBLP) to improve the accuracy and, in turn, stability of the aggregate growth measures. I will discuss the implementation of EBLP for aggregate student achievement growth including the statistical models and estimation methods. I will also discuss the results of applying the method to data in two states.

https://www.linkedin.com/in/dan-mccaffrey-1654809/