Prediction of police performance: a regression model.

Abstract

The purpose of this study is to develop regression models to predict the performance of police officers using standardized psychological tests. It has not been clearly established that the various police occupations form a homogeneous whole; therefore, an effective predictor of performance for police officers of a particular city may be of little value In a somewhat different police environment. Previous research In this area has contributed little that might serve as a basis for the development of a comprehensive theory of police performance. One-hundred nine police officers were randomly divided into a research group (N=55) and a cross-validation group (N=54). Two hundred predictor variables were taken from seven standardized tests to develop regression models to pre-diet the performance of police officers based on performance evaluations. Five criteria were pulled from the performance evaluations and were used In this study. The criteria Included task, Initiative, quality, judgment, and cooperation. Personality and Interest inventory's combined with aptitude tests were em.' ployed In this research to Isolate effective predictors of police performance. Cross-validation was performed on the criterion cooperation. The results of this study indicate significance . [E.< .01] on all five criteria and also with the cross-validation sample. The results Indicate It is possible to develop regression models to predict pollee performance and will provide a basis for further research.