Empirical evidence to the robustness of the analysis of variance (ANOVA) concerning violation of the normality assumption is presented by means of Monte Carlo methods. High-quality samples underlying normally, rectangularly, and exponentially distributed basic populations are created by drawing samples which consist of random numbers from respective generators, checking their goodness of fit, and allowing only the best 10% to take part in the investigation. A one-way fixed-effect design with three groups of 25 values each is chosen. Effect-sizes are implemented in the samples and varied over a broad range. Comparing the outcomes of the ANOVA calculations for the different types of distributions, gives reason to regard the ANOVA as robust. Both, the empirical type I error α and the empirical type II error β remain constant under violation. Moreover, regression analysis identifies the factor “type of distribution” as not significant in explanation of the ANOVA results.

No abstract

Self‐ratings of personality predict academic success above general intelligence. The present study replicated these findings and investigated the increment of other‐ratings or intentionally distorted self‐ratings. Participants (N = 145) had to compile a personality questionnaire twice. First they were given neutral instructions. The second time they were asked to imagine a specific applicant setting. Furthermore, two peers rated each participant. Additionally, verbal, numerical and figural reasoning scores were obtained. Grades on a statistics exam obtained 2 months later served as the criterion. Results replicated prior findings and showed incremental validity for self‐ and other‐rated personality, which was stable after controlling for intelligence. Faking had no impact on the domain‐score level, but results on the facet‐score level were less encouraging. Copyright © 2010 John Wiley & Sons, Ltd.

Several meta-analyses combine an extensive amount of research concerned with predicting training success. General mental ability is regarded as the best predictor with specific abilities or tests explaining little additional variance. However, only few studies measured all predictors within one sample. Thus, intercorrelations were often estimated based on other studies. Moreover, new methods for correcting range restriction are now available. The present meta-analyses used samples derived from a German company in which applicants for different apprenticeships were tested with an intelligence structure test, specific ability tests as well as a structured and an unstructured interview. Therefore, intercorrelations between different assessment tools did not have to be estimated from other data. Results in the final examination, taking place at least 2 years after the original assessment, served as criterion variable. The dominant role of general mental ability was confirmed. However, specific abilities were identified that can be used as valuable additions. Job complexity moderated some of the relationships. Structured interviews were found to have good incremental validity over and above general mental ability. Unstructured interviews, on the other hand, performed poorly. Practical implications are discussed.

No abstract