ERIC Number: ED336427
Record Type: RIE
Publication Date: 1990-Dec
Reference Count: N/A
Congeneric Models and Levine's Linear Equating Procedures.
Brennan, Robert L.
In 1955, R. Levine introduced two linear equating procedures for the common-item non-equivalent populations design. His procedures make the same assumptions about true scores; they differ in terms of the nature of the equating function used. In this paper, two parameterizations of a classical congeneric model are introduced to model the variables in the Levine procedures for the external and internal anchor cases. The models differ in the constraints imposed on certain effective test length parameters, as well as assumptions made about one covariance term. This modelling leads to simple expressions for true-score variances, reliabilities, and Angoff error variances. Applying these two parameterizations of the classical congeneric model with the Levine assumptions leads to general equations for both Levine procedures and both external and internal anchor cases that involve ratios of the effective test length parameters. The role of synthetic population weights for both Levine procedures is considered, along with an alternative interpretation of one Levine procedure. Multiple equations, one table, and one appendix support the discussion. A 19-item list of references is included. (Author/SLD)
Descriptors: Equated Scores, Equations (Mathematics), Mathematical Models, Research Design, Test Length, Testing Problems, True Scores
ACT Research Report Series, P.O. Box 168, Iowa City, IA 52243.
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: American Coll. Testing Program, Iowa City, IA.
Identifiers: Anchor Tests; Congeneric Tests; Levine Equating Method; Linear Equating Method
Note: Revised version of a paper presented at the Annual Meeting of the Psychometric Society (Princeton, NJ, June 2-7, 1990).