DSpace DSpace

University of Minnesota Digital Conservancy >
University of Minnesota - Twin Cities >
Applied Psychological Measurement >
Volume 17, 1993 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/11299/116376

Title: Scale shrinkage in vertical equating
Authors: Camilli, Gregory
Yamamoto, Kentaro
Wang, Ming-mei
Issue Date: 1993
Citation: Camilli, Gregory, Yamamoto, Kentaro & Wang, Ming-mei. (1993). Scale shrinkage in vertical equating. Applied Psychological Measurement, 17, 379-388. doi:10.1177/014662169301700407
Abstract: As an alternative to equipercentile equating in the area of multilevel achievement test batteries, item response theory (IRT) vertical equating has produced unexpected results. When expanded standard scores were obtained to link the Comprehensive Test of Basic Skills and the California Achievement Test, the variance of test scores diminished both within particular grade levels from fall to spring, and also from lower to upper grade levels. Equipercentile equating, on the other hand, has resulted in increasing variance both within and across grade levels, although the increases are not linear across grade levels. Three potential causes of scale shrinkage are discussed, and a more comprehensive, model-based approach to establishing vertical scales is described. Test data from the National Assessment of Educational Progress were used to estimate the distribution of ability at grades 4, 8, and 12 for several math achievement subtests. For each subtest, the variance of scores increased from grade 4 to grade 8; however, beyond grade 8 the results were not uniform. Index terms: developmental scores, equating, IRT scaling, maximum likelihood estimation, National Assessment of Educational Progress (NAEP), scale shrinkage, vertical equating.
URI: http://purl.umn.edu/116376
Appears in Collections:Volume 17, 1993

Files in This Item:

File Description SizeFormat
v17n4p379.pdf1.07 MBPDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.