Learning a more distributed representation of the input feature space is a powerful method to boost the performance of a given predictor. Often this is accomplished by partitioning the data into homogeneous groups by clustering so that separate models could be trained on each cluster. Intuitively each such predictor is a better representative of…

Empirically determines if two approaches, i.e., individual predictor information versus group information, would yield different predictive results, and since the second approach involved the additional expense of grouping whether the prediction of criterion measures by individual data could be enhanced by the addition of group data. (Author/RC)

A self-report inventory was compared with a situational test as a predictor of the verbal behavior of individual members of small interpersonal skills training groups. As hypothesized, the situational test was a better predictor than was the self-report inventory. A powerful social conformity effect may have operated in both the situational test…