Integrating differential evolution optimization to cognitive diagnostic model estimation

Abstract

A log-linear cognitive diagnostic model (LCDM) is estimated via a global optimization approach- differential evolution optimization (DEoptim), which can be used when the traditional expectation maximization (EM) fails. The application of the DEoptim to LCDM estimation is introduced, explicated, and evaluated via a Monte Carlo simulation study in this article. The aim of this study is to fill the gap between the field of psychometric modeling and modern machine learning estimation techniques and provide an alternative solution in the model estimation.