Advances in Applications of Item Response Theory to Clinical Assessment
Advances in Applications of Item Response Theory to Clinical Assessment
复制标题
DOI：
10.1037/pas0000597
复制
发表时间：
2019-12-01
影响因子：
3.6
通讯作者：
Thomas, Michael L.
中科院分区：
文献类型：
--
作者：
Thomas, Michael L.
项目反应理论(IRT)正走在开发、评估和评分临床测量方法的前沿。资助机构和测试开发人员经常支持IRT工作，这一理论已与该领域的技术进步密切相关。因此，对IRT的熟悉与心理健康研究和实践越来越相关。但目的是什么呢？本文综述了IRT在临床测量中应用的进展，以努力确定可归因于该方法学的切实改进。虽然IRT与经典测试理论和因子分析有相似之处，但当应用于测量挑战时，该方法有一定的实际好处，但也有局限性。主要机会包括使用计算机化的适应性测试来防止条件性测量错误，使用多维模型来防止对分数的误解，以及分析不同的项目功能以防止偏见。虽然这些方法和技术曾经只是作为未来的可能性进行讨论，但由于最近以IRT为重点的临床研究的支持，它们现在可以使用。尽管如此，在将IRT的方法和技术广泛传播到心理健康研究和实践方面仍有许多工作要做。临床医生一直不愿完全接受这种方法，特别是在前瞻性试验开发和适应性项目管理方面。IRT技术的广泛使用将需要心理测量学家、临床医生和其他利益相关者之间的持续合作。也有许多机会扩展方法论，特别是在将现代测量理论与人格、认知心理学和神经科学的模型相结合方面。
Item response theory (IRT) is moving to the forefront of methodologies used to develop, evaluate, and score clinical measures. Funding agencies and test developers are routinely supporting IRT work, and the theory has become closely tied to technological advances within the field. As a result, familiarity with IRT has grown increasingly relevant to mental health research and practice. But to what end? This article reviews advances in applications of IRT to clinical measurement in an effort to identify tangible improvements that can be attributed to the methodology. Although IRT shares similarities with classical test theory and factor analysis, the approach has certain practical benefits, but also limitations, when applied to measurement challenges. Major opportunities include the use of computerized adaptive tests to prevent conditional measurement error, multidimensional models to prevent misinterpretation of scores, and analyses of differential item functioning to prevent bias. Whereas these methods and technologies were once only discussed as future possibilities, they are now accessible because of recent support of IRT-focused clinical research. Despite this, much work still remains in widely disseminating methods and technologies from IRT into mental health research and practice. Clinicians have been reluctant to fully embrace the approach, especially in terms or prospective test development and adaptive item administration. Widespread use of IRT technologies will require continued cooperation among psychometricians, clinicians, and other stakeholders. There are also many opportunities to expand the methodology, especially with respect to integrating modern measurement theory with models from personality and cognitive psychology as well as neuroscience.