What mediation analysis can (not) do

By Klaus Fiedler, Malte Schott, T. Meiser. 2011

558 citations recorded by the source corpus.

Subfields: Social Psychology, Sociology and Political Science, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/9787cd2fe7cf2e9dcdf3d89ea50be90f41238f31

How researchers see this paper

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

In Social Psychology

1. Richard E. Petty
2. P. Briñol
3. S. van der Linden
4. Andrew Luttrell
5. B. Wagner
6. Charlotte Ursula Tate
7. Matthew H. Goldberg
8. Anthony Leiserowitz

In Sociology and Political Science

1. S. van der Linden
2. P. Briñol
3. Richard E. Petty
4. S. Rosenthal
5. Matthew T. Ballew
6. Matthew H. Goldberg
7. Abel Gustafson
8. Edward Maibach

In Statistics and Probability

1. P. Briñol
2. Edward Maibach
3. B. Wagner
4. Charlotte Ursula Tate
5. Richard E. Petty
6. Matthew H. Goldberg
7. S. van der Linden
8. Anthony Leiserowitz

Citations in the corpus

• Making it moral: Merely labeling an attitude as moral increases its strength (2016, result): “We note, however, that some have criticized the use of manipulation checks as mediators (Fiedler, Schott, & Meiser, 2011), so we caution against drawing strong conclusions from these results.”
• On the Overuse and Misuse of Mediation Analysis: It May Be a Matter of Timing (2015, methodology): “Those authors concluded by arguing that several helpful determinants of actual mediators might be ‘‘design features like experimental manipulation with random assignment, longitudinal analysis of temporal antecedence, or other control mechanisms (e.g., Rubin, 2006)’’ (Fiedler et al., 2011, p. 1236).”
• The Greta Thunberg Effect: Familiarity with Greta Thunberg predicts intentions to engage in climate activism in the United States (2021, background): “First, because we rely on an observational design, we cannot confidently offer any causal conclusions, account for alternative explanations (Fiedler et al., 2011), or discount the possibility of an exogenous variable driving the observed relationships.”
• Meaningful Mediation Analysis: Plausible Causal Inference and Informative Communication (2017, methodology): “Second, adding potential confounders to the mediation model, based on the theory of their potential influence on the mediator and outcome independent of the treatment, can make the unconfoundedness condition more plausible (Fiedler, Schott, and Meiser 2011; Pearl 2009; Westfall and Yarkoni 2016).”