The Probabilistic-Inputs, Noisy Conjunctive Model for Cognitive Diagnosis

• In Event: New Developments and Applications in Cognitive Diagnosis Models

Abstract

To measure individual difference in latent attributes more precisely, this study proposed a new cognitive diagnosis model (CDM), which is referred as the probabilistic-inputs, noisy conjunctive (PINC) model, by treating the deterministic binary latent attributes as probabilistic, and directly estimating the probability in the model. Simulation studies were conducted to evaluate parameter recovery of the new model, and the results revealed that the parameters can be recovered well with WinBUGS. An empirical example of the Examination for the Certificate of Proficiency in English was provided to demonstrate applications of the new model.

Authors

• Peida Zhan, Beijing Normal University

• Wen-Chung Wang, The Hong Kong Institute of Education

• Xiaomin Li, The Hong Kong Institute of Education

• Yufang Bian, Beijing Normal University