ERIC Number: ED521120
Record Type: Non-Journal
Publication Date: 2011-May-13
Reference Count: 14
Design of Value-Added Models for IMPACT and TEAM in DC Public Schools, 2010-2011 School Year. Final Report
Isenberg, Eric; Hock, Heinrich
Mathematica Policy Research, Inc.
This report presents the value-added models that will be used to measure school and teacher effectiveness in the District of Columbia Public Schools (DCPS) in the 2010-2011 school year. It updates the earlier technical report, "Measuring Value Added for IMPACT and TEAM in DC Public Schools." The earlier report described the methods used to estimate teacher effectiveness in DCPS during the 2009-2010 school year, the first year of the IMPACT assessment system in DCPS. Working together with officials at DCPS as well as with external peer reviewers Eric Hanushek of the Hoover Institution at Stanford University and Tim Sass of Florida State University, the authors modified two aspects of the value-added model in order to meet the needs of DCPS: (1) They changed the method of accounting for team teaching in the teacher model to increase the number of students accounted for in some teachers' value-added measures. The new method is also more computationally robust. Value-added estimates produced by both methods do not differ substantially; and (2) At the request of DCPS, the value-added models no longer account for a student's gender when estimating teachers' and schools' effectiveness. Based on an analysis of data from previous years, the authors expect the change to have a negligible effect on value-added estimates for schools and teachers. Apart from these modifications, the school and teacher value-added models that they estimated during the 2009-2010 school year are identical to those they plan to estimate for the 2010-2011 school year. The authors provide a detailed description of the two changes made to the value-added models for the 2010-2011 school year and then present a nontechnical overview of the resulting models used to estimate teacher and school effectiveness, showing how key features of the models help produce results designed to be as accurate and fair as possible. In the remaining chapters of this report, they update the earlier mechanical details of value-added models they will estimate with data from the 2010-2011 school year, incorporating the two changes that they have made to the method. In Chapter II, they present a description of the data, and, in Chapter III, they focus on the statistical methods. (Contains 16 footnotes.) [For related report, "Measuring School and Teacher Value Added for IMPACT and TEAM in DC Public Schools. Final Report," see ED521118.]
Descriptors: Public Schools, Teacher Effectiveness, School Effectiveness, Models, Achievement Gains, Evaluation Criteria, Evaluation Methods, Student Evaluation, Teacher Evaluation, Measurement Objectives, Measurement Techniques, Program Descriptions, Research Reports, Regression (Statistics), Error of Measurement, Background, Comparative Analysis, Comparative Testing, Scores
Mathematica Policy Research, Inc. P.O. Box 2393, Princeton, NJ 08543-2393. Tel: 609-799-3535; Fax: 609-799-0005; e-mail: firstname.lastname@example.org; Web site: http://www.mathematica-mpr.com
Publication Type: Reports - Evaluative
Education Level: Elementary Secondary Education
Sponsor: District of Columbia Public Schools, Washington, DC.
Authoring Institution: Mathematica Policy Research, Inc.
Identifiers - Location: District of Columbia
IES Cited: ED544673; ED544269; ED544674; ED548024