The Causal Mediation Formula—A Guide to the Assessment of Pathways and Mechanisms

By Judea Pearl. 2012

401 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

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

In Statistics and Probability

Citations in the corpus

Path-Specific Counterfactual Fairness (2018, methodology): “Pearl (2001; 2012) and Sh-pitser (2013) indicate how and when the PSE can be expressed through integrations over conditional distributions involving only observed variables.”
Counterfactual Graphical Models for Longitudinal Mediation Analysis With Unobserved Confounding (2012, background): “ of path-speciﬁc eﬀects in the time-varying treatment setting. Identiﬁable path-speciﬁc eﬀects are expressed in terms of the path-speciﬁc g-formula, which is a generalization of the mediation formula [4]. The natural next step is to extend existing statistical estimation techniques for the g-formula”
TRYGVE HAAVELMO AND THE EMERGENCE OF CAUSAL CALCULUS (2014, neutral): “2 (see, for example, Greenland and Pearl, 2011; Kyono, 2010; or Pearl, 2010a, 2010b, 2012a).”
Interpretation and identification of causal mediation. (2014, neutral): “…include M in the regression, and estimate the partial regression coefficient R YT·M 5 Readers familiar with nonparametric SEM as introduced in Pearl (2009b) (2010b) (2012a), Petersen et al. (2006), and VanderWeele (2009) may go directly to the Interpretable Conditions for Identification…”
Statistical mediation analysis with a multicategorical independent variable. (2014, background): “…certain alternative explanations, and more complex statistical approaches than we discuss here can be used in non-experimental studieswhen causal inference is less justified due to limitations of the design (such as non-random assignment; see, for example, Hong, 2012; Muth en, 2011; Pearl, 2012).”
Two-condition within-participant statistical mediation analysis: A path-analytic framework. (2017, methodology): “Using simple principles of linear modeling (though other analytical approaches are possible; Imai, Keele, & Tingley, 2010; Pearl, 2010, 2012), mediation analysis is used to quantify and test the pathways of influence from X to Y.”
Causal Mediation Analysis (2011, background): “Robins JM, Greenland S. (1992).”
EIGHT MYTHS ABOUT CAUSALITY AND STRUCTURAL EQUATION MODELS (2013, neutral): “19 by Berk et al. this volume) – which is none other but the SEM’s interpretation of structural equations (Haavelmo 1943; Blau and Duncan 1967; Pearl 2011c).”
Causal and Counterfactual Inference (2018, methodology): “(18) which came to be known as the mediation formula (Pearl, 2012).”
CAUSAL INFERENCE WITH A GRAPHICAL HIERARCHY OF INTERVENTIONS (2014, neutral): “which recovers the well-known mediation formula [12].”