ERIC Number: ED480556
Record Type: Non-Journal
Publication Date: 2003-Apr
Evidentiary Relationships among Data-Gathering Methods and Reporting Scales in Surveys of Educational Achievement. CSE Technical Report.
Mislevy, Robert J.
Large-scale surveys of educational attainment gather data about the proficiencies of a sample of students to support inferences about the distribution in the populations. Several approaches to gathering data have been used, each with its own advantages and disadvantages. Several scales have also been used to bring results together from different students and different test forms. This paper lays out the evidentiary relationships between data gathered under five methods and inferences framed in terms of six reporting metrics. "Marketbasket" reporting receives special attention. The five methods are: (1) a single test form; (2) parallel forms; (3) tau-equivalent forms; (4) congeneric forms; and (5) unconstrained items. The six reporting matrices discussed are: (1) observed scores on a particular administrable test form; (2) true scores on a particular administrable test form; (3) observed scores on a particular synthetic test form; (4) true scores on a particular synthetic test form; (5) point estimates on a latent variable scale; and (6) latent variable scales themselves. (Contains 8 tables, 15 figures and 43 references.) (Author/SLD)
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Sponsor: Office of Educational Research and Improvement (ED), Washington, DC.
Authoring Institution: California Univ., Los Angeles. Center for the Study of Evaluation.; National Center for Research on Evaluation, Standards, and Student Testing, Los Angeles, CA.