Unwarranted Inferences From Statistical Mediation Tests – An Analysis Of Articles Published In 2015
收藏资源简介：
Recent attempts to improve on the quality of psychological research focus on good practices required for statistical<br> significance testing. The scrutiny of theoretical reasoning, though superordinate, is largely neglected, as<br> exemplified here in a common misunderstanding of mediation analysis. Although a test of a mediation model<br> X -> Z -> Y is conditional on the premise that the model applies, alternative mediators Z′, Z″, Z‴ etc. remain<br> untested, and other causal models could underlie the correlation between X, Y, Z, researchers infer from a single<br> significant mediation test that they have identified the true mediator. A literature search of all mediation analyses<br> published in 2015 in Sciencedirect shows that the vast majority of studies neither consider alternative causal<br> models nor alternative mediator candidates. Ignoring that mediation analysis is conditional on the truth of the<br> focal mediation model, they pretend to have demonstrated that Z mediates the influence of X on Y. Recommendations<br> are provided for how to overcome this dissatisfying state of affairs.
