Mediation Testing in Management Research
回顾并批评了过去25年5本顶级组织学期刊中409项研究的中介分析实践，发现多数完全和部分中介的推断偏离统计学家推荐的方法，且结果报告不完整，为未来研究提供改进建议。
The authors review and critique the conduct and reporting of mediation analyses in 409 studies published in five leading organization studies journals over the past 25 years. The aim of the study is to learn from past practice and to use that knowledge to signal to researchers the importance of correctly applying mediation tests as well as to facilitate the valid testing of mediation models and the reporting of mediation results in future studies. The authors content code their sample for a wide range of characteristics and find that the majority of inferences of full and partial mediation are based on testing procedures that deviate significantly from procedures recommended by statisticians. In addition, the reporting of results is often incomplete and inefficient. The authors discuss and evaluate the findings of the study and make recommendations for future testing and reporting of results for mediation models.