Prediction with single event versus aggregate data

Abstract

The impact of statistical information on predictive judgment was studied in a cue probability learning (CPL) task. Two kinds of aggregate information about criterion events were used: the conditional mean (ZM) and the conditional interquartile range (ZR). The single event information was the exact criterion value for one randomly selected past case (ZO). Results showed that ZMand ZR increased prediction consistency and accuracy and reduced bias while ZO led to more appropriate cue weighting but lower consistency and accuracy. When ZM, ZR, and ZO were all provided, the unique benefits of single-event and aggregate data were combined. This was true even for subjects without any prior task experience. When able to select only one of ZM, ZR, and ZO, judges most often chose aggregate information, particularly ZR. However, the statistical information was underutilized. Recommendations for aiding predictive judgment are made.