CONFUSION OF CONFIDENCE-INTERVALS AND CREDIBILITY INTERVALS IN METAANALYSIS

A review of 30 meta-analyses that have been conducted in organizational behavior and human resource management using procedures described by Hunter, Schmidt, and Jackson (1982) suggests that there is confusion regarding the use and interpretation of confidence intervals and credibility intervals. This confusion can lead to conflicting conclusions about the relationships between variables. The most frequent mistake has been the attempt to address the accuracy of the estimate of the mean effect size using "confidence intervals" based on the corrected standard deviation instead of on the standard error of the mean r or d. The corrected standard deviation should be used to generate a "credibility interval" to assess the extent to which moderators might account for the unexplained variance in effect sizes.