Models for Value-Added Modeling of Teacher Effects

Abstract

The use of complex value-added models that attempt to isolate the contributions of teachers or schools to student development is increasing. Several variations on these models are being applied in the research literature, and policy makers have expressed interest in using these models for evaluating teachers and schools. In this article, we present a general multivariate, longitudinal mixed-model that incorporates the complex grouping structures inherent to longitudinal student data linked to teachers. We summarize the principal existing modeling approaches, show how these approaches are special cases of the proposed model, and discuss possible extensions to model more complex data structures. We present simulation and analytical results that clarify the interplay between estimated teacher effects and repeated outcomes on students over time. We also explore the potential impact of model misspecifications, including missing student covariates and assumptions about the accumulation of teacher effects over time, on key inferences made from the models. We conclude that mixed models that account for student correlation over time are reasonably robust to such misspecifications when all the schools in the sample serve similar student populations. However, student characteristics are likely to confound estimated teacher effects when schools serve distinctly different populations.

Class-size reduction policies and the quality of entering teachers

“…Viewed in this light, the challenges of VAM estimation are those faced in identifying causal relationships with panel data more generally. VAM estimation has proven to be difficult in non-experimental settings and there is no consensus on what the best model of student achievement is or the best approach to estimating the portion attributable to teachers (McCaffrey et al 2004;Kane & Staiger 2008, Rothstein 2009, 2010Koedel & Betts 2011). Much of this difficulty stems from the non-random assignment of students to teachers both within and across schools.…”

Prejudice in the classroom: a longitudinal analysis of anti-immigrant attitudes

“…The current research largely treats the effects of context on attitude development as if it is consistent over time, when it is possible that they are also dynamically changing, having different effects sizes at different times, or disappearing entirely as real-world conditions change. Historically, value-added models analysing longitudinal data have addressed this issue to study academic achievement in relation to classroom context and teacher performance on students (Doran and Lockwood 2006;McCaffrey et al 2004), however, this method has not yet been applied to attitude development. As previous research has noted, there is an age effect on prejudice, but the ages that apply to this dataset (∼13-17 years) have been found to be a stabilizing time for adolescent's attitudes (Raabe and Beelmann 2011).…”

Do Typical RCTs of Education Interventions Have Sufficient Statistical Power for Linking Impacts on Teacher Practice and Student Achievement Outcomes?

“…Importantly, the classroom-level error θ ij y reflects classroom-level variation in student test score gains, including both persistent and transitory effects (such as a "barking dog" effect that influences all students in the classroom at the time the test is administered). The literature provides separate estimates for these two effects using longitudinal student and teacher data and estimating models similar to (1) (see, for example, Goldhaber 2002;Hanushek et al 2005;Jacob and Lefgren 2005;McCaffrey et al 2004;Nye et al 2004;and Rothstein 2009). Estimates of the persistent classroom effects may capture teacher-, student-, and school-related factors that influence student achievement.…”