Isobel M Cameron1, Neil W Scott, Mats Adler, Ian C Reid. 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.
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.
Authors: Alan Tennant; Massimo Penta; Luigi Tesio; Gunnar Grimby; Jean-Louis Thonnard; Anita Slade; Gemma Lawton; Anna Simone; Jane Carter; Asa Lundgren-Nilsson; Maria Tripolski; Haim Ring; Fin Biering-Sørensen; Crt Marincek; Helena Burger; Suzanne Phillips Journal: Med Care Date: 2004-01 Impact factor: 2.983
Authors: Stephen Houghton; Ida Marais; Simon C Hunter; Annemaree Carroll; David Lawrence; Carol Tan Journal: Qual Life Res Date: 2020-09-15 Impact factor: 3.440
Authors: Stéphanie Bourion-Bédès; Raymund Schwan; Vincent Laprevote; Alex Bédès; Jean-Louis Bonnet; Cédric Baumann Journal: Health Qual Life Outcomes Date: 2015-10-24 Impact factor: 3.186