Assessing Measurement Invariance in ASWB Exams: Regulatory Research Proposal to Advance Equity

Gerald Bean and Matthew Peter DeCarlo
Additional contact information
Matthew Peter DeCarlo: Radford University

No dk5at, SocArXiv from Center for Open Science

Abstract: The purpose of the proposed study is to investigate the measurement equivalence, or invariance, of social work licensing exams for persons of color as compared with White test takers, across different age groups, and differences based on English as a primary language. At present, ASWB statistically investigates the fairness of its exams at the item-level only, moving question by question. This approach to investigating measurement bias is inadequate on its own, and the psychometric standards cited by ASWB require exam developers to investigate multivariate problems at the content area or test-level–i.e., differential test functioning (DTF). Our proposal was submitted to the ASWB Regulatory Research Initiative to Advance Equity, but the merits of the proposal were not evaluated by the committee. Although our ($0 budget) proposal stated “the only technical resources required for this project are the free and open source R statistics software, a computer, and exam performance data from ASWB,” DeCarlo et al., 2023, p. 8), ASWB did not provide data to our research team because “it was not clear to the committee that you were requesting data other than what is publicly available on the ASWB website” (J. Henckel, personal communication). Using simulated data, we demonstrate an approach to exam fairness and measurement equivalency testing that follows best practices to address vast pass rate disparities for historically and presently excluded groups.

Date: 2023-09-16
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://osf.io/download/6505ae7a0fbdf70399313d6c/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:socarx:dk5at

DOI: 10.31219/osf.io/dk5at

Access Statistics for this paper

More papers in SocArXiv from Center for Open Science
Bibliographic data for series maintained by OSF ().