ERIC Number: ED127330
Record Type: Non-Journal
Publication Date: 1975-Sep
Reference Count: N/A
Equating Reading Tests With the Rasch Model. Volume I, Final Report.
Rentz, R. Robert; Bashaw, W. L.
In order to determine if Rasch Model procedures have any utility for equating pre-existing tests, this study reanalyzed the data from the equating phase of the Anchor Test Study which used a variety of equipercentile and linear model methods. The tests involved included seven reading test batteries, each having from one to three levels and two forms, and each having a vocabulary and comprehension subtest. There were 28 form-level combinations possible. Therefore, of concern was the simultaneous equating of 28 tests for each of vocabulary, comprehension, and total scores. Seven objectives characterized the study and are elaborated on in separate sections of this report. The objectives were to: (1) describe a methodology for test equating using the Rasch Model, (2) describe basic item analysis data for each test in the Anchor Test Study data base, (3) evaluate the fit of the Rasch Model with respect to those tests that were part of the data base, (4) investigate the stability of Rasch Model parameter estimates under conditions of varying sample size and sample composition, (5) provide tables of equated based on Rasch Model methods, (6) estimate the equating error associated with the use of these equating methods, and (7) compare the results of equating with those obtained in the Anchor Test Study. (RC)
Publication Type: Reports - Research
Education Level: N/A
Sponsor: National Center for Education Statistics (DHEW), Washington, DC.
Authoring Institution: Georgia Univ., Athens. Educational Research Lab.