Comparison of Bookmark Difficulty Locations Under Different Item Response Models
- 1 January 2004
- journal article
- other
- Published by SAGE Publications in Applied Psychological Measurement
- Vol. 28 (1), 25-47
- https://doi.org/10.1177/0146621603259903
Abstract
In the bookmark standard-setting procedure, judges place “bookmarks” in a reordered test booklet containing items presented in order of increasing difficulty. Traditionally, the bookmark difficulty location (BDL) is on the trait continuum where, for dichotomous items, there is a two-thirds probability of a correct response and, for a score of k on a polytomous item, there is a two-in-three probability of a score of k or higher. General formulas for the computation of BDLs were derived for five item response theory models—namely, the 1PL and 3PL for dichotomous items and the partial credit (PC), generalized partial credit (GPC), and graded response (GR) models for polytomous items and for any response probability (RP) value. These formulas were then used to compare the ordering of items’ BDLs under the 1PL-PC, 3PL-GPC, and 3PL-GR models for RPs of 1/2, 2/3, and 4/5. Results are discussed, and guidelines for practitioners are offered. Index terms: item response theory, bookmark standard setting, item difficulty, item mapping.Keywords
This publication has 14 references indexed in Scilit:
- A Comparison of Angoff and Bookmark Standard Setting MethodsJournal of Educational Measurement, 2002
- On Score Locations of Binary and Partial Credit Items and Their Applications to Item Mapping and Criterion-Referenced InterpretationJournal of Educational and Behavioral Statistics, 1998
- A Brief History of Item Theory ResponseEducational Measurement: Issues and Practice, 1997
- Scaling Performance Assessments: A Comparison of One‐Parameter and Two‐Parameter Partial Credit ModelsJournal of Educational Measurement, 1996
- An NCME Instructional Module on: Setting Passing ScoresEducational Measurement: Issues and Practice, 1996
- A Generalized Partial Credit Model: Application of an EM AlgorithmApplied Psychological Measurement, 1992
- The Utility of a Modified One-Parameter IRT Model With Small SamplesApplied Measurement in Education, 1991
- Application of Item Response Models to Criterion-Referenced AssessmentApplied Psychological Measurement, 1983
- A rasch model for partial credit scoringPsychometrika, 1982
- The Next Stage in Educational AssessmentEducational Researcher, 1982