ERIC Number: ED383716
Record Type: Non-Journal
Publication Date: 1990-Dec
Reference Count: N/A
Aligning Score Scales for Achievement Tests in Multiple Content Areas.
Cook, Linda L.; And Others
As a result of a recent College Board Admissions Testing Program Achievement Test scaling study, L. L. Cook and others recommended that the practice of sampling only high school juniors taking the achievement tests in June might be expanded to include sophomores and that a two-stage scaling procedure be evaluated. The two-stage procedure would include a first stage involving scaling tests on a within-cluster basis, but the second stage would involve taking the results of the first stage and following it with a second scaling in which scaled scores from the first stage would be used as input. This study experimentally evaluated these scaling recommendations, separating the Achievement Tests into a language test cluster and a nonlanguage test cluster. In addition, high school sophomores were added to the samples. Results indicate that addition of the sophomores does not improve the relationship between Achievement Test scores and the scaling covariates. There is evidence to suggest that the use of empirical values for the reference group and the use of a two-stage scaling procedure may improve the alignment of the Achievement Test scales. Seven tables and three figures present analysis results. (Contains nine references.) (SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: Educational Testing Service, Princeton, NJ.
Identifiers - Assessments and Surveys: College Board Achievement Tests