A psychometric investigation into the use of an adaptation of the Ghiselli predictability index in personnel selection

[摘要] ENGLISH ABSTRACT:The field of human resources involves continuous decision-making regarding thematching of the workforce with the workplace, since this match determines individuals'motivation to perform the actions associated with the workplace.If, at the time of the decision, the decision maker could obtain information on endperformance, the chances of achieving the desired results would be increased. However,personnel selection is complicated by the obvious fact that information on endperformance is not available at the time of the selection decision. All such decisions thusinvolve predictions about people's performance. The classic validity model forms thefoundation of all prediction in as far as the strength of the relationship between thepredictor of performance and the actual performance determines the accuracy of thepredictor.Over time, numerous possibilities have been considered on how to increase themagnitude of this relationship as experienced through the validity coefficient, mostlyinvolving modifications and/or extensions to the standard regression model. Aninteresting and challenging alternative to the usual multiple-regression based attemptsmay be found in the work of Ghise11i (1956, 1960a, 1960b). He has chosen to improveprediction directly through the development of a composite predictability index thatexplains variance in the prediction errors resulting from an existing prediction model. Itwould, however, appear as if the procedure has found very little, if any, practicalacceptance, partly attributed to the fact that the predictability index failed to significantlyexplain unique variance in the criterion when added to a model already containing one ormore predictors.Resultantly, based on the Ghiselli idea, this research investigates the possibility ofmodifying such a predictability index so that it does significantly explain unique variancein the criterion when added to a model already containing one or more predictors. Inaddition, the study investigates whether the expansion of the prediction model iswarranted by examining the effect the increase in subject predictability has on thepredictive validity of the selection procedure, as well as the monetary effect it has on theutility of the procedure. Hypotheses are tested to determine the possibility of developingan index from a personality measurement that shows a strong and significant correlationwith the residuals computed from the regression of the criterion on an ability predictor; todetermine if the addition of the index to an ability predictor significantly explainsvariance in the criterion measurement that is not yet explained by the ability predictorrelationships, and to determine whether this ability is affected by the direction in whichthe index has been developed. Furthermore, hypotheses are tested to determine theincrement on validity and selection utility.The data for the analysis was obtained from Psytech (SA), where a validation study wasperformed at the Gordon Institute of Business Science using the Apil-B ability test, theCritical Reasoning Test Battery and the Organisational Personality Profile measurementsto predict the performance of 100 MBA students.The results of the analysis confirmed Ghiselli' s earlier findings that the traditionalpredictability index does not significantly explain variance in the criterion residual whenadded to the selection battery. However, by modifying the Ghiselli procedure, the studyfound that the index was able to significantly explain variance when added to a batteryalready containing the predictor. When the index is based on the real values of theresiduals, the addition of the predictability index to the model significantly explainsunique variance in the criterion, but not so when based on the absolute values of theresiduals. It also indicated that the inclusion of the predictability index to the predictionmodel created a substantial increase in the validity of the selection procedure and that theincrease in validity translated into a noteworthy improvement in utility.Conclusions are drawn from the obtained results and recommendations are made forfuture research.

[发布机构] Stellenbosch University