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

Isobel M. Cameron, Neil W. Scott, Mats Adler, Ian C. Reid

Research output: Contribution to journalArticle

13 Citations (Scopus)

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 χ2 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.
Original languageEnglish
Pages (from-to)2883-2888
Number of pages15
JournalQuality of Life Research
Volume23
Issue number10
Early online date22 May 2014
DOIs
Publication statusPublished - Dec 2014

Fingerprint

Anxiety
Logistic Models
Regression Analysis
Depression
Research Personnel
Primary Health Care
Quality of Life
Research

Keywords

  • differential item functioning
  • depression
  • anxiety
  • questionnaire
  • item bias

Cite this

@article{7cc971c6d37d4974b72c8c312af2330f,
title = "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",
abstract = "PurposeIt 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.MethodThree methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel χ2 procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners.ResultsThree 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.ConclusionsOrdinal 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.",
keywords = "differential item functioning, depression, anxiety, questionnaire, item bias",
author = "Cameron, {Isobel M.} and Scott, {Neil W.} and Mats Adler and Reid, {Ian C.}",
note = "We would like to thank the primary care participants and general practices who kindly took part in the original study from which the data were collected. The original research from which the data presently analysed were collected was funded by the Centre for Change and Innovation, of the then Scottish Executive; and from Support for Science funding, Grampian NHS Research and Development. The present methodological investigations were conducted without additional funding.",
year = "2014",
month = "12",
doi = "10.1007/s11136-014-0719-3",
language = "English",
volume = "23",
pages = "2883--2888",
journal = "Quality of Life Research",
issn = "0962-9343",
publisher = "Springer",
number = "10",

}

TY - JOUR

T1 - A comparison of three methods of assessing differential item functioning (DIF) in the Hospital Anxiety Depression Scale

T2 - ordinal logistic regression, Rasch analysis and the Mantel chi-square procedure

AU - Cameron, Isobel M.

AU - Scott, Neil W.

AU - Adler, Mats

AU - Reid, Ian C.

N1 - We would like to thank the primary care participants and general practices who kindly took part in the original study from which the data were collected. The original research from which the data presently analysed were collected was funded by the Centre for Change and Innovation, of the then Scottish Executive; and from Support for Science funding, Grampian NHS Research and Development. The present methodological investigations were conducted without additional funding.

PY - 2014/12

Y1 - 2014/12

N2 - PurposeIt 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.MethodThree methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel χ2 procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners.ResultsThree 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.ConclusionsOrdinal 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.

AB - PurposeIt 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.MethodThree methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel χ2 procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners.ResultsThree 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.ConclusionsOrdinal 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.

KW - differential item functioning

KW - depression

KW - anxiety

KW - questionnaire

KW - item bias

U2 - 10.1007/s11136-014-0719-3

DO - 10.1007/s11136-014-0719-3

M3 - Article

VL - 23

SP - 2883

EP - 2888

JO - Quality of Life Research

JF - Quality of Life Research

SN - 0962-9343

IS - 10

ER -