The dependability of electrophysiological measurements of performance monitoring in a clinical sample: A generalizability and decision analysis of the ERN and Pe.

Psychometric studies of the ERN, CRN, Pe, and Pc ERPs are increasing. Coherent integration of these results is difficult with classical test theory because the definition of error depends on the measure of reliability. This study used generalizability theory, which extends the ideas of classical test theory, as a framework for evaluating the influence of psychopathology and number of trials on dependability of measurement. Participants included 34 people meeting criteria for major depression, 29 meeting criteria for an anxiety disorder, and 319 controls. For all ERPs, within-person variance was larger than between-person variance across groups, indicating many trials are needed for adequate dependability (at least 13). Slightly fewer trials were needed to achieve adequate dependability in the control group than the pathology groups. Regions of interest had higher dependability than single sensors.