Validity Generalization

To ensure that researchers and practitioners understand the degree of accuracy of their decisions, collecting validation evidence for the measures they use is crucial. Validity coefficients, correlations that represent the linear relationship between scores on a predictor and scores on a criterion, are quantitative indices of the value of an assessment in predicting future outcomes. Validity generalization is an application of meta-analysis that is used to estimate the mean and variance of a collection of validity coefficients. The validity generalization estimate of the mean validity coefficient is likely to be more accurate than local validation studies that often have limited sample sizes, outcome variables with measurement error, and possibly data with a restricted range of scores. This entry details the value of summarizing individual validation ...