Department of Education, University of California, Los Angeles, 3141 Moore Hall, 457 Portola Avenue, Los Angeles, CA, 90024, USA.
University of California, Berkeley, CA, USA.
Behav Res Methods. 2020 Feb;52(1):224-235. doi: 10.3758/s13428-019-01221-5.
In this paper, we propose a specialized confirmatory mixture IRT model to analyze complex cognitive assessment data that is designed to evaluate adolescents' developmental stages in deductive reasoning. The model is specified for the following purposes: (1) to measure multiple deductive reasoning traits, (2) to identify adolescents' differential developmental stages based on their ability levels in the multiple dimensions, (3) to quantify the differences in dimension-specific performance between developmental stages, and (4) to examine the difficulty levels of test design factors. A Bayesian estimation of the model is described. The overall goodness-of-fit of the model is assessed as well as its parameter recovery to validate the application of the model to the data.
在本文中，我们提出了一种专门的确认性混合IRT 模型，用于分析旨在评估青少年演绎推理发展阶段的复杂认知评估数据。该模型具有以下特定目的：(1) 测量多个演绎推理特征，(2) 根据多维能力水平识别青少年的不同发展阶段，(3) 量化发展阶段之间特定维度表现的差异，以及 (4) 检验测试设计因素的难度水平。描述了模型的贝叶斯估计。评估了模型的整体拟合优度及其参数恢复情况，以验证模型在数据中的应用。
