Format

Send to

Choose Destination
Qual Life Res. 2014 Dec;23(10):2883-8. doi: 10.1007/s11136-014-0719-3. Epub 2014 May 22.

A comparison of three methods of assessing differential item functioning (DIF) in the Hospital Anxiety Depression Scale: ordinal logistic regression, Rasch analysis and the Mantel chi-square procedure.

Author information

1
Psychiatry Group, Division of Applied Medicine, Royal Cornhill Hospital, University of Aberdeen, Aberdeen, AB25 2ZH, Scotland, UK, i.m.cameron@abdn.ac.uk.

Abstract

PURPOSE:

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.

METHOD:

Three methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel χ(2) procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners.

RESULTS:

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.

CONCLUSIONS:

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.

PMID:
24848597
DOI:
10.1007/s11136-014-0719-3
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center