What Are the Consequences If the Assumption of Independent Observations Is Violated in Reliability Generalization Meta-Analysis Studies?

摘要

This study was conducted to evaluate alternative analysis strategies for the meta-analysis method of reliability generalization when the reliability estimates are not statistically independent. Five approaches to dealing with the violation of independence were implemented: ignoring the violation and treating each observation as independent, calculating one mean or median from each study, selecting only one observation per study, and using a mixed-effects model. Monte Carlo methods were used to simulate samples under known and controlled population conditions. The results suggest that the type of approach does not have a noticeable impact on the accuracy of the reliability results but that researchers should be cautious when the intraclass correlation is relatively large. The simulations in this study also resulted in very poor confidence band coverage.