The NPCD-CAT Lab resides in the Department of Educational Psychology at the University of Minnesota. There are currently four active members in the lab, working on various projects. Our mission is to develop the theoretical foundations of efficient and easy-to-use assessment tools that help improve the quality and effectiveness of instruction in classrooms. The research recently supported by the NSF CAREER grant focuses on the development of nonparametric methods for cognitive diagnosis and the nonparametric CD-CAT algorithms, with the goal to implement these cutting-edge innovations in cognitive diagnosis to classrooms. The details of the major projects can be found in Research & Projects.

However, any CAT system must prove itself vis-a-vis the challenges of real-world applications. Hence, the research team also developed the web app Computerized Adaptive Testing and Learning for Cognitive Diagnosis (CATL-CD) based on the nonparametric CD-CAT algorithms. The CATL-CD web app has been tested, enhanced, and was implemented in Dr. Chia-Yi Chiu’s online Statistics course when she was part of the lab to provide individualized learning packages and feedback for students. The research associated with the NPCD-CAT has been disseminated through training sessions (e.g., 2019 NCME), publications, and presentations. The recent presentations are posted below.

News

  • Item-Cloning Algorithm for CD-CAT, December 2021
    Computerized Adaptive Testing and Learning for Cognitive Diagnosis (CATL-CD), recently developed by the PI, is an app for E-learning that combines online instruction with close monitoring of students’ learning progress. After every curricular unit each student is presented with an individualized set of items to assess which topics she has mastered and which require further… Continue reading Item-Cloning Algorithm for CD-CAT, December 2021
  • 2021 NCME Presentation
    Nonparametric Classification Method for Multiple-Choice Items in Cognitive Diagnosis Abstract A nonparametric classification method for multiple-choice items (MC-NPC) for cognitive diagnosis (CD) is proposed in the study. The preliminary simulation study shows that the MC-NPC method results in higher correct classification rates than the traditional CD methods for dichotomous data and outperforms the MC-DINA model… Continue reading 2021 NCME Presentation
  • 2021 IMPS Presentation
    Nonparametric Classification Method for Multiple-Choice Items in Cognitive Diagnostic Assessments Abstract Cognitive diagnostic models (CDMs) aim to estimate the mastery and nonmastery of attributes for examinees. Numerous CDMs have been developed; however most of them can only be used to analyze dichotomous responses. Multiple-choice (MC) items are always dichotomized to fit the data with these… Continue reading 2021 IMPS Presentation
  • GSE Brown Bag, Spring 2021
    Prof. Chiu presented the grant research at GSE Brown Bag in Spring 2021.