A0332
Title: Dynamic cognitive diagnostic frameworks: A general model for learning
Authors: Zichu Liu - Beijing Normal University (China) [presenting]
Shiyu Wang - University of Georgia (United States)
Shumei Zhang - Beijing Normal University (China)
Tao Qiu - Beijing Normal University (China)
Houping Xiao - Robinson College of Business/GSU (United States)
Abstract: In education, understanding students' learning trajectories is essential for educators to monitor and enhance their progress effectively. With the advent and widespread use of computer-based testing, researchers now have access to rich and varied datasets that offer deeper insights into student performance. A novel general dynamic cognitive diagnostic model that integrates response accuracy and response times is introduced. The aim is to distinguish between different learning and testing behaviors, allowing for the estimation of students' learning trajectories concerning their proficiency levels in various assessed skills over time. Comprising two key components, a dynamic transition model assessing the transition probabilities of students' attributes and a mixture fluency model evaluating students' attribute profiles, the proposed model is rigorously validated through extensive simulation studies. These studies demonstrate the model's efficacy in providing valuable insights into students' learning trajectories. Furthermore, the proposed model is applied to a real dataset derived from a spatial rotation diagnostic test, further showcasing its practical utility in educational settings. Through its comprehensive approach and rigorous validation, this model emerges as a valuable tool for educators and researchers alike, offering nuanced insights into students' learning progress and behavior dynamics.
