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
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
复制标题
DOI：
10.1007/s11136-014-0719-3
复制
发表时间：
2014-12-01
影响因子：
3.5
通讯作者：
Reid, Ian C.
中科院分区：
文献类型：
--
作者：
Cameron, Isobel M.;Scott, Neil W.;Reid, Ian C.
幸福感和生活质量的测量量表仅表现出最小的项目功能差异（DIF），这对临床实践和研究非常重要。DIF发生在不同的人群在与预期的量表属性匹配后对量表中的项目给予不同程度的认可。我们调查了评估DIF的常用方法的等效性或其他方面。测量年龄和性别相关DIF的三种方法（有序逻辑回归，Rasch分析和Mantel chi（2）程序）应用于与1个样本有关的医院焦虑抑郁量表（HADS）数据，068名患者咨询初级保健医生。三种方法都标记了三个项目，无论是年龄还是性别，相关的DIF具有一致的作用方向;另外三个项目确定不符合使用至少一种方法的重要DIF的更严格标准。当应用严格的标准显着DIF，有序逻辑回归是稍微不太敏感。有序逻辑回归，Rasch分析和列联表方法产生一致的结果时，确定DIF在HADS抑郁和HADS焦虑量表。无论采用何种方法，研究者在解释结果时应结合统计学显著性、DIF效应的大小和研究者的判断。
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.