The identification of concealed memories using the event-related potential and implicit behavioral measures: a methodology for prediction in the face of individual differences

Abstract

The development and validation of an event-related potential (ERP) memory assessment procedure is detailed. The procedure identifies learned material with high rates of accuracy, whether or not subjects give intentional responses indicating they had previously learned it. Because the traditional analysis of variance approach fails to provide probabilistic conclusions about any given individual, Bayesian posterior probabilities were computed, indicating the probability for each and every person that material was learned. The method was developed on a sample of 20 subjects, and then cross-validated on two additional samples of 20 subjects each. Across the three samples, the method correctly defined over 94% of learned material as learned, and misclassified 4% of the unlearned material. Additionally, in a simple oddball task performed by the same subjects, the method classified rare and frequent material with perfect accuracy. Finally, combining two implicit behavioral measures--mean reaction time and the number of incorrect responses--in Bayesian fashion yielded classification accuracy that actually exceeded that of the ERP-based procedure overall, but the two methods provided identical accuracy in classifying the most critical material as recognized.