Abstract
Researchers often need to obtain an estimate of the relationship between a predictor and a criterion under conditions where the magnitude of the correlation coefficient has been distorted by an error component in the predictor and criterion variables (attenuation) and restriction in the range of the predictor. The present paper delineates the factors that influence the joint impact of attenuation and range restriction on the magnitude of the correlation coefficient, and establishes a theoretical framework for the generation of appropriate correction formulas. A set of equations for making joint attenuation and range restriction corrections when there is attenuation and restriction on the predictor is presented. Finally, it is shown that the concept of predictor reliability changes in selection situations because of the correlation between error and true scores.
Get full access to this article
View all access options for this article.