How and why criteria defining moderators and mediators differ between the Baron & Kenny and MacArthur approaches.

By H. Kraemer, M. Kiernan, Marilyn J. Essex, David J. Kupfer. Health Psychology, 2008

647 citations recorded by the source corpus.

Subfields: Clinical Psychology, Developmental and Educational Psychology, Social Psychology

View Paper: https://www.semanticscholar.org/paper/7883ecdd710bad7718c702d0eb874ea5bfd019f5

How researchers see this paper

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

In Clinical Psychology

In Developmental and Educational Psychology

In Social Psychology

Citations in the corpus

A general approach to causal mediation analysis. (2010, neutral): “Kraemer et al. (2008) argued that in addition to ␤ ˆ 2 , either ␥ ˆ or ␬ ˆ must be statistically indistinguishable from zero in order to conclude that average mediation effects exist.”
Understanding how and why psychotherapy leads to change (2009, background): “Extensive attention is accorded statistical analyses and the conditions that need to be met in order to conclude that mediation has been demonstrated (e.g., Kraemer et al., 2008; MacKinnon, 2008).”
Interactions do not only tell us when, but can also tell us how: Testing process hypotheses by interaction (2011, background): “…DIFFERENCES OF TPIS WITH AND TO THE MACARTHUR APPROACH The distinction between B and TV makes it clear that it is important to discuss recent work presenting what has become known as the MacArthur approach to mediation and moderation (Kraemer, Wilson, Fairburn, & Agras, 2002; Kraemer et al., 2008).”
Mediation analysis allowing for exposure-mediator interactions and causal interpretation: theoretical assumptions and implementation with SAS and SPSS macros (2013, methodology): “The counterfactual approach coincides with the criteria for mediation of the MacArthur approach (Kraemer et al., 2008) but provides actual direct and indirect effect estimates that combine to a total effect and makes clear the no-unmeasured-confounding assumptions needed for a causal interpretation.”
Total, Direct, and Indirect Effects in Logit and Probit Models (2013, background): “However, a special case arises when the predictor variable and the mediator variable are interacted (Kraemer et al. 2008).”
The Mediation Formula: A Guide to the Assessment of Causal Pathways in Nonlinear Models (2011, methodology): “This becomes more transparent when we examine the standard linear model to which a multiplicative term xz is added, as is done, for example, in the analyses of Kraemer et al. (2008), Jo (2008), and Preacher et al. (2007).”
Assessing Mediational Models: Testing and Interval Estimation for Indirect Effects (2010, methodology): “Finally, we also study the classical null testing approach in the mediational context, which constitutes of a series of causal steps used to evaluate the mediational model ( Baron & Kenny, 1986 ; Judd & Kenny, 1981 ; Kenny et al, 1998 ; Kraemer, Kiernan, Essex, & Kupfer, 2008 ; MacKinnon et al, ”
The Logic of Causal Inference (2010, background): “; Rubin, 2009; Kraemer et al., 2008; Fleming and DeMets, 1996; Green et al., 2010).”
Key Results of Interaction Models with Centering (2011, background): “…is often defined as a relationship such that an independent variable X1 causes a mediating variable X2 which then in turn causes the dependent variable Y ; see Bauer et al. (2006); MacKinnon and Luecken (2008); Kraemer et al. (2008) for a full discussion. term (Cohen 1978; Cohen et al. 2003).”
Mindfulness Practice, Rumination and Clinical Outcome in Mindfulness-Based Treatment (2014, methodology): “Our analysis of treatment mediation was rooted in the conceptual approach advocated by Kraemer specifically for randomized controlled trials (Kraemer et al. 2008).”
The Causal Mediation Formula—A Guide to the Assessment of Pathways and Mechanisms (2012, methodology): “These conclusions are not readily discernible from the structural equations without the guidance of the Mediation Formula and, indeed, they have not been addressed in previous analyses of this interaction model (Jo 2008; Judd and Kenny 1981, 2010; Kraemer et al. 2008; MacKinnon 2008).”
Childhood Adversity, Adult Stressful Life Events, and Risk of Past-Year Psychiatric Disorder: A Test of the Stress Sensitization Hypothesis in a Population-based Sample of Adults (2009, background): “Kraemer et al. (2008) suggest that when a correlation exists between two exposures (e.g. CAs and adult stressors), a statistical interaction between those exposures in predicting an outcome should be interpreted as evidence of mediation rather than moderation.”