Journal
QUALITY OF LIFE RESEARCH
Volume 23, Issue 10, Pages 2883-2888Publisher
SPRINGER
DOI: 10.1007/s11136-014-0719-3
Keywords
Differential item functioning; Depression; Anxiety; Questionnaires; Item bias
Categories
Funding
- Centre for Change and Innovation
- Scottish Executive
- Grampian NHS Research and Development
Ask authors/readers for more resources
It is important for clinical practice and research that measurement scales of well-being and quality of life exhibit only minimal differential item functioning (DIF). DIF occurs where different groups of people endorse items in a scale to different extents after being matched by the intended scale attribute. We investigate the equivalence or otherwise of common methods of assessing DIF. Three methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel chi(2) procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners. Three items were flagged by all three approaches as having either age- or sex-related DIF with a consistent direction of effect; a further three items identified did not meet stricter criteria for important DIF using at least one method. When applying strict criteria for significant DIF, ordinal logistic regression was slightly less sensitive. Ordinal logistic regression, Rasch analysis and contingency table methods yielded consistent results when identifying DIF in the HADS depression and HADS anxiety scales. Regardless of methods applied, investigators should use a combination of statistical significance, magnitude of the DIF effect and investigator judgement when interpreting the results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available