Reversing Arrows in Mediation Models Does Not Distinguish Plausible Models

By F. Thoemmes. 2015

208 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/a41ad83140f9442babfb54643925fc4d8f4f1eb4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

1. Rik Pieters
2. S. Bamberg
3. Maarten Kroesen

In Management Science and Operations Research

1. Sabrina Zirkel
2. M. Murphy
3. Malte Friese
4. Rik Pieters
5. Shrija Dirghangi
6. Shelley R. Hart
7. Alexander E Wong
8. Marc van Essen

In Statistics and Probability

1. M. Murphy
2. Malte Friese
3. Rik Pieters
4. Shrija Dirghangi
5. Shelley R. Hart
6. Alexander E Wong
7. S. Bamberg

Citations in the corpus

• Self-concept clarity mediates the effects of adverse childhood experiences on adult suicide behavior, depression, loneliness, perceived stress, and life distress (2018, background): “SCC ->SE) to determine causal ordering is an invalid inferential practice which cannot distinguish better models due to model equivalency (Lemmer & Gollwitzer, 2016; Thoemmes, 2015).”
• Meaningful Mediation Analysis: Plausible Causal Inference and Informative Communication (2017, background): “As a case in point, Thoemmes (2015) found in a large simulation study that an inspect-and-select strategy in mediation analysis identified the known, true model in less than 30% of the cases for a basic mediation model where influence in each of the three paths could have two directions.”
• The role of STEM professors’ mindset beliefs on students’ anticipated psychological experiences and course interest. (2020, background): “…were measured after fair treatment concerns, sense of belonging, and evaluative concerns and are conceptually considered downstream outcomes of the psychological effects (see Fiedler, Harris, & Schott, 2018 and Thoemmes, 2015 for why reverse mediation analyses should be interpreted with caution).”
• Breaking the Habit: On the Highly Habitualized Nature of Meat Consumption and Implementation Intentions as One Effective Way of Reducing It (2018, background): “However, correlational support of course does not establish causality, and there is now a growing literature on the issues related to causal inference based on correlational analyses, structural equation modeling, and especially mediation analyses (see Grice, Cohn, Ramsey, & Chaney, 2015; Tate, 2015”