The “true” indirect effect won't (always) stand up: When and why reverse mediation testing fails

详细信息    查看全文

• 作者：Gunnar Lemmer ; ^{gunnar.lemmer@uni-marburg.de} ; Mario Gollwitzer
• 关键词：Mediation processes ; Causality ; Reverse mediation ; Monte Carlo simulation
• 刊名：Journal of Experimental Social Psychology
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：69
• 期：Complete
• 页码：144-149
• 全文大小：360 K
• 卷排序：69

文摘

Tests of mediation hypotheses (i.e., X ➔ M ➔ Y) are widespread in social psychology In many cases, "X ➔ Y ➔ M" is a plausible alternative model A common practice is to compare both indirect effects (reverse mediation testing) Monte Carlo simulations show that this approach often leads to wrong conclusions This especially applies when "M" is measured less reliably than "Y"