Madison Matthew J, Bradshaw Laine P
University of Georgia, Athens, GA, USA.
Educ Psychol Meas. 2015 Jun;75(3):491-511. doi: 10.1177/0013164414539162. Epub 2014 Jun 22.
Diagnostic classification models are psychometric models that aim to classify examinees according to their mastery or non-mastery of specified latent characteristics. These models are well-suited for providing diagnostic feedback on educational assessments because of their practical efficiency and increased reliability when compared with other multidimensional measurement models. A priori specifications of which latent characteristics or are measured by each item are a core element of the diagnostic assessment design. This item-attribute alignment, expressed in a Q-matrix, precedes and supports any inference resulting from the application of the diagnostic classification model. This study investigates the effects of Q-matrix design on classification accuracy for the log-linear cognitive diagnosis model. Results indicate that classification accuracy, reliability, and convergence rates improve when the Q-matrix contains isolated information from each measured attribute.
诊断分类模型是一种心理测量模型，旨在根据考生对特定潜在特征的掌握或未掌握情况对其进行分类。与其他多维测量模型相比，这些模型因其实际效率和更高的可靠性，非常适合在教育评估中提供诊断反馈。每个项目所测量的潜在特征是什么的先验规范是诊断评估设计的核心要素。以Q矩阵表示的这种项目-属性一致性，先于并支持诊断分类模型应用所产生的任何推断。本研究调查了Q矩阵设计对对数线性认知诊断模型分类准确性的影响。结果表明，当Q矩阵包含来自每个测量属性的独立信息时，分类准确性、可靠性和收敛率会提高。
