Illustrating the Utility of Differential Bundle Functioning Analyses to Identify and Interpret Group Differences on Achievement Tests

Abstract

What is differential bundle functioning and how is this different from differential item functioning? Can test specifications be used to identify and aid in the interpretation of differential bundle functioning? How can differential bundle functioning lead to an improved understanding of why groups perform differently on achievement tests?

A Psychometric Analysis of an Inventory for Evaluating Students' Leadership Skills

“…Thus, the SIBTEST displayed a slightly poorer performance than the other two procedures for all items (SIBTEST = 0.051, p< .05), with average power of 42.6% compared to approximately 45% for both GMH and LDFA. This result is consistent with the findings of Gierl et al, (2001) who reported that in comparison with MH, which they referred to as "the conservative procedure", LR could flag a large number of items as exhibiting DIF. Also, as Gierl et al, (2003) have found, LR has excellent Type I error rates which is a reassuring point for the researchers who choose LR as their DIF detection method.…”

“…Jodoin and Gierl (2001) also emphasized that while LR has comparable power to MH and SIBTEST in detecting uniform DIF, it is superior in power for detecting non-uniform DIF. In addition, Gierl et al, (2001) found that effect size measures (for MH, SIBTEST and LR) were highly correlated across DIF procedures except the measure for non-uniform DIF, which could only be assessed by LR. Altogether, these findings can provide tacit confirmation as to the superiority of GMH and LDFA over SIBTEST.…”

Do Major Field of Study and Cultural Familiarity Affect TOEFL® iBT Reading Performance? A Confirmatory Approach to Differential Item Functioning

“…It requires a hypothesis that some of the items could be "bundled" for DBF analysis based on certain common characteristics. Many of the more recent studies provide successful examples of applying DBF in explaining differential functioning occurrences (e.g., Abbott, 2007;Gierl, 2005;Gierl, Bisanz, Bisanz, Boughton, & Khaliq, 2001;Gierl, Bisanz, Bisanz, & Boughton, 2003;Douglas, Roussos, & Stout, 1996). These studies either adopt an a priori approach which involves theoretical speculations of which items should be grouped for bundle analysis and then confirm the hypothesis, or a post-hoc approach that often involves content examination of items after the DIF results are available to search for any common characteristics of the DIF items.…”

A Review of Recent Developments in Differential Item Functioning

“…These included iterative purification procedures under various conditions: (a) different matching criteria, (b) different analytic units (i.e., item-, bundle-, or testlet-level), and (c) different assumptions about tests' dimensional structures (e.g., Gierl, Bisanz, Bisanz, Boughton, & Khaliq, 2001;Mazor, Kanjee, & Clauser, 1995;Oshima, Raju & Flowers, 1997;Wainer, 1995). Furthermore, variations of the aforementioned procedures were developed to study non-uniform DIF (Li & Stout, 1996).…”