A question I frequently get asked by both new and experienced Partners in the assessment industry is why the number of 30 incumbents is recommended as a minimum sufficient sample size for creating custom concurrent performance models.
One of the purposes of the study was to provide the scientific community and the world with a more accurate understanding of what small, medium, and large effect sizes (correlations symbolized by the letter “r”) are in applied Psychology.
When companies select an assessment for prehire screening of job applicants, they typically have some knowledgeable person download a performance model from the test publisher’s library of patterns or they create a concurrent performance model using assessment results from a representative group of incumbents.
The spotlight I am shining on this table and figure number two in the article is to demonstrate the almost unlimited types of variables that can be studied and end up rendering predictive value. Figure 2 in the study is an abbreviated hierarchical variable taxonomy the authors used to classify 30 years of variables. It references 4,869 variable nodes.