Journal article
Structural Zeros and Their Implications With Log-Linear Bivariate Presmoothing Under the Internal-Anchor Design
Journal of educational measurement, Vol.54(2), pp.145-164
07/01/2017
DOI: 10.1111/jedm.12138
Abstract
In equating, when common items are internal and scoring is conducted in terms of the number of correct items, some pairs of total scores (X) and common-item scores (V) can never be observed in a bivariate distribution of X and V; these pairs are called structural zeros. This simulation study examines how equating results compare for different approaches to handling structural zeros. The study considers four approaches: the no-smoothing, unique-common, total-common, and adjusted total-common approaches. This study led to four main findings: (1) the total-common approach generally had the worst results; (2) for relatively small effect sizes, the unique-common approach generally had the smallest overall error; (3) for relatively large effect sizes, the adjusted total-common approach generally had the smallest overall error; and, (4) if sole interest focuses on reducing bias only, the adjusted total-common approach was generally preferable. These results suggest that, when common items are internal and log-linear bivariate presmoothing is performed, structural zeros should be maintained, even if there is some loss in the moment preservation property.
Details
- Title: Subtitle
- Structural Zeros and Their Implications With Log-Linear Bivariate Presmoothing Under the Internal-Anchor Design
- Creators
- Hyung Jin Kim - Univ Iowa, CASMA, Lindquist Ctr South 210, Iowa City, IA 52242 USARobert L. Brennan - Univ Iowa, CASMA, Lindquist Ctr South 210, Iowa City, IA 52242 USAWon-Chan Lee - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Journal of educational measurement, Vol.54(2), pp.145-164
- Publisher
- Wiley
- DOI
- 10.1111/jedm.12138
- ISSN
- 0022-0655
- eISSN
- 1745-3984
- Number of pages
- 20
- Language
- English
- Date published
- 07/01/2017
- Academic Unit
- Psychological and Quantitative Foundations; Center for Advanced Studies in Measurement and Assessment
- Record Identifier
- 9984371293102771
Metrics
1 Record Views