This article addresses likely error rates for measuring teacher and school performance in the upper elementary grades using value-added models applied to student test score gain data. Using formulas based on ordinary least squares and empirical Bayes estimators, error rates for comparing a...

This working paper outlines four options available to policymakers for addressing co-teaching in a value-added model: the partial credit method, the teacher team method, the full roster method, and the full roster-plus method. The authors discuss why the first two methods are impractical, and...

At the request of Pittsburgh Public Schools and the Pittsburgh Federation of Teachers, Mathematica has developed value-added models that aim to estimate the contributions of individual teachers and schools to the achievement of their students.

This working paper helps to address the issue of isolating the effect of each teacher on student achievement when the student is taught the same subject by more than one teacher. This paper considers and compares three methods—Partial Credit Method, Teacher Team Method, and Full Roster...

This report describes the value-added models (VAMs) created for the Pittsburgh Public Schools and the Pittsburgh Federation of Teachers. Pittsburgh's VAMs use not only state assessments but also course-specific assessments, student attendance, and course completion rates, aiming to produce...

This working paper outlines four options available to policymakers for addressing co-teaching in a value-added model: the partial credit method, the teacher team method, the full roster method, and the full roster-plus method. The authors discuss why the first two methods are impractical, and...