Reevaluating the SIBTEST Classification Heuristics for Dichotomous Differential Item Functioning. (April 2022)

• Record Type: Journal Article
• Authors: Weese, James D.; Turner, Ronna C.; Ames, Allison; Crawford, Brandon; Liang, Xinya
• Is Part Of: Educational and psychological measurement. Volume 82:Number 2(2022)
• Page Start: 307
• Page End: 329
• Publication Date: 2022-04
• Subjects: SIBTEST -- differential item functioning -- DIF; Educational tests and measurements -- Periodicals; Psychological tests -- Periodicals; 151.205
• DOI: 10.1177/00131644211017267
• Languages: English
• ISSNs: 0013-1644

Abstract

A simulation study was conducted to investigate the heuristics of the SIBTEST procedure and how it compares with ETS classification guidelines used with the Mantel–Haenszel procedure. Prior heuristics have been used for nearly 25 years, but they are based on a simulation study that was restricted due to computer limitations and that modeled item parameters from estimates of ACT and ASVAB tests from 1987 and 1984, respectively. Further, suggested heuristics for data fitting a two-parameter logistic model (2PL) have essentially went unused since their original presentation. This simulation study incorporates a wide range of data conditions to recommend heuristics for both 2PL and three-parameter logistic (3PL) data that correspond with ETS's Mantel–Haenszel heuristics. Levels of agreement between the new SIBTEST heuristics and Mantel–Haenszel heuristics were similar for 2PL data and higher than prior SIBTEST heuristics for 3PL data. The new recommendations provide higher true-positive rates for 2PL data. Conversely, they displayed decreased true-positive rates for 3PL data. False-positive rates, overall, remained below the level of significance for the new heuristics. Unequal group sizes resulted in slightly larger false-positive rates than balanced designs for both prior and new SIBTEST heuristics, with rates less than alpha levels for equal ability distributions and unbalanced designs versus false-positive rates slightly higher than alpha with unequal ability distributions and unbalanced designs.