Statistical classification for cognitive diagnostic assessment: an artificial neural network approach

Abstract

The purpose of the current investigation was to describe how the artificial neural networks (ANNs) can be used to interpret student performance on cognitive diagnostic assessments (CDAs) and evaluate the performances of ANNs using simulation results. CDAs are designed to measure student performance on problem-solving tasks and provide useful diagnostic information about cognitive skill acquisition. But for CDA to realise its potential as a formative testing method, substantial progress must be made in the development of cognitive models that characterise students’ knowledge structures and processes skills, the construction of high-quality test items that precisely measure the nature of the knowledge and skills as specified in the cognitive models, as well as the advancement of psychometric techniques that allow us to accurately interpret student performance. The current investigation focuses on the third component as we examine the use of ANNs as a powerful nonparametric statistical method for diagnostic classification.

Keywords:

• Artificial neural networks
• cognitive diagnostic assessment
• multilayer perceptron
• self-organising map
• statistical classification

Disclosure statement

No potential conflict of interest were reported by the authors.

Acknowledgement

Preparation of this article was supported by a grant from the Social Sciences and Humanities Research Council of Canada. Grantees undertaking such projects are encouraged to express freely their professional judgement. This article, therefore, does not necessarily represent the positions or the policies of the Canadian government, and no official endorsement should be inferred.