Aggregation and beyond: Some basic issues on the prediction of behavior


  • The writing of this paper was supported by NIMH Research Grant MH-01293-22 and NSF Research Grant BNS 78-12336. I wish to express my appreciation for the constructive comments of Jonathan M. Cheek, Douglas T. Kenrick, L. Alan Sroufe, and Stephen G. West.

Requests for reprints should be sent to Seymour Epstein, Department of Psychology, University of Massachusetts, Amherst, Massachusetts 01003.


Failure to appreciate the role that aggregation plays in increasing reliability and validity and in establishing the range of generalization of findings has resulted in misunderstandings about the stability of behavior across time and situations, and in the conduct of experiments that produce results that tend to be neither generalizable nor replicable. Appropriate aggregation can reduce error variance associated with the unrepresentativeness of individual stimuli, situations, occasions, judges, items of behavior, and subjects. Inappropriate aggregation can result not only in a loss of information but also in a reduction in reliability as well as validity. Different approaches to prediction with single items of behavior are discussed, and it is concluded that single items tend to be too unreliable and too narrow in scope to measure broad dispositions such as traits. A major emphasis is that behavior is often so highly situationally specific that unless this is taken into account by procedures such as aggregation over situations and/or occasions, or by the investigation of events that are so highly ego-involving that experimental effects dominate situation-ally unique effects, results will tend to be unreplicable or ungeneralizable, no matter what their level of statistical significance.