Date of Original Version
Abstract or Description
Cognitive models are often used to predict the average performance of a population. For many purposes, however, generating predictions of individual performance is crucial. We propose a methodology in which the ACT-R architecture is extended, through the setting of architectural parameters that represent individual differences, into a model of individual behavior. This approach can provide a vast range of predictive and diagnostic capabilities from a modest initial investment of resources.
F. Detje, D. Doerner, & H. Schaub (Eds.), In Proceedings of the Fifth International Conference on Cognitive Modeling, 287-288.