Value-Added Teacher Estimates as Part of Teacher Evaluations - Exploring the Effects of Data and Model Specifications on the Stability of Teacher Value-added Scores

Oct 15, 2026

Teacher value-added estimates (VAEs) are examined as tools for teacher-performance indicators in evaluation and accountability systems, focusing on how sensitive VAEs are to data inputs and modeling choices. The study tests three conditions affecting stability: adjustments for students’ prior learning, estimation from single versus multiple cohorts, and the number of students contributing to each teacher’s VAE. Using data from a large U.S. school district and VAEs for 3,651 fifth-grade mathematics teachers, results show about two thirds remain in the same performance group across conditions, while specification choices explain substantial reclassification shares.

LanguageEnglish

CategoryExam

FormatPDF

Pages39

Reading Time1 h 38 min

AccessFree to download

Abstract

Study design and conditions

Data source and teacher sample

Findings on stability and reclassifications

Policy implications

SPECIAL ISSUE Value-Added: What America’s Policymakers Need to Know and Understand education policy analysis archives A peer-reviewed, independent, open access, multilingual journal Arizona State University | Volume 21 Number 7 | January 29, 2013 | ISSN 1068-2341 | | --- | --- | --- | Value-added Teacher Estimates as Part of Teacher Evaluations: Exploring the Effects of Data and Model Specifications on the Stability of Teacher Value-added Scores Nicole B. Kersting Mei-kuang Chen University of Arizona United States of America James W. Stigler University of California, Los Angeles United States of America Citation: Kersting, N. B., Chen, M., & Stigler, J. W. (2012). Education Policy Analysis Archives, 21(7) . This article is part of EPAA/AAPE’s Special Issue on Value-Added: What America’s Policymakers Need to Know and Understand, Guest Edited by Dr. Audrey Amrein-Beardsley and Assistant Editors Dr. Clarin Collins, Dr. Sarah Polasky, and Ed Sloat. Retrieved [date], from [http://epaa.asu.edu/ojs/article/view/1167](http://epaa.asu.edu/ojs/article/view/1167) . Abstract: If teacher value-added estimates (VAEs) are to be used as indicators of individual teacher performance in teacher evaluation and accountability systems, it is important to understand how much VAEs are affected by the data and model specifications used to estimate them. In this study we explored the effects of three conditions on the stability of VAEs and evaluated their relative impact. We varied how we accounted for differences among students in their prior learning; whether we estimated VAEs from single or multiple cohorts of students; and the number of students contributing to the VAE for each teacher. Using data from one of the largest school districts in the nation, we created a single, complete data set and used it to estimate several sets of VAEs for each of the 3651 5th grade mathematics teachers. We found that approximately two thirds of teachers’ were stable in that they remained in the same performance group across all conditions. We also found that differences in number of students used for VAEs accounted for up to one third of teacher reclassifications into different performance groups; single versus multiple cohort models accounted for about one fifth; and different methods for controlling for student prior learning accounted for about one sixth (16%) of teacher reclassifications. We relate our findings to characteristics of our data and discuss implications for educational policy. Keywords: Value-added Analysis, Value-added Models; Value-added Estimates; Stability; Teacher Evaluations; Accountability. Las estimaciones de valor agregado docente como parte de las evaluaciones docentes: Explorando los efectos de los datos y las especificaciones de los modelos en la estabilidad de las puntuaciones de valor agregado docentes Resumen: Si estimaciones de valor añadido docente (VADs) van a ser utilizadas como indicadores de rendimiento de los docentes en cada evaluación de los profesores y en los sistemas rendición de cuentas, es importante entender cómo los VADs son afectados por los datos recogidos y las especificaciones de los modelos utilizados para estimarlos. En este estudio hemos explorado los efectos de tres condiciones para la estabilidad de VADs y evaluar sus impactos relativos. Hemos variado cómo se estimaron las diferenciasentre los estudiantes en sus aprendizajes previos; hemos estimado VADs de una omúltiples promociones de estudiantes; y el número de estudiantes que contribuyen a lade cada uno de los VADs de los profesores. Utilizando los datos de uno de los mayores distritos escolares de la nación, hemos creado un conjunto único de datos completo y loutilizamos para estimar varios conjuntos de único para cada uno de los 3651 profesores de matemáticas de 5to. Grado. Encontramos que aproximadamente dos terceras partes de los maestros se mantuvieron estables y que permanecieron en el mismo grupo derendimiento

FAQs

Why does the study focus on data and model specifications in teacher value-added estimates?

To determine how much VAEs change when different data handling and modeling specifications are used, which affects their credibility as performance indicators in evaluation systems.

What three conditions were varied in estimating teacher VAEs?

Accounting for students’ prior learning differences, using single versus multiple student cohorts, and changing the number of students contributing to each teacher’s VAE.

What did the study find about the stability of teacher value-added performance groups?

Approximately two thirds of teachers were stable, staying in the same performance group across all tested conditions, while differences in model inputs explained meaningful reclassification fractions.

Oct 15, 2026

Uploaded by anakgang17