A general identification condition for causal effects

By Jin Tian, Judea Pearl. 2002

420 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Algorithmic recourse under imperfect causal knowledge: a probabilistic approach (2020, background): “Moreover, if only a partial graph is available or some relations are known to be confounded, one will need to restrict recourse actions to the subset of interventions that are still identiﬁable [36, 37, 41].”
Causal inference in statistics: An overview (2009, background): “All existing criteria for identification are special cases of the one defined in the following theorem: Theorem 2 (Tian and Pearl, 2002).”
Counterfactual Graphical Models for Longitudinal Mediation Analysis With Unobserved Confounding (2012, methodology): “then the intervention on A can be represented by replacing equation (8) by another equation that sets A to a constant a.”
Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution (2018, background): “For models where the “back-door” criterion does not hold, a symbolic engine is available, called do-calculus, which predicts the effect of policy interventions whenever feasible, and exits with failure whenever predictions cannot be ascertained with the specified assumptions (Pearl, 1995; Tian and P”
Algebraic problems in structural equation modeling (2016, methodology): “3 have generalizations to nonlinear structural equation models [56, 66].”
Causal Transportability with Limited Experiments (2013, methodology): “…for z-Transportability Some of the previous analyses of identifiability, zidentifiability, and transportability [Kuroki and Miyakawa, 1999; Tian and Pearl, 2002; Shpitser and Pearl, 2006; Huang and Valtorta, 2006; BP, 2012b; 2012a] will be useful in the algorithmization of…”
Transportability of Causal Effects: Completeness Results (2012, methodology): “R is not trivially transportable due to the confounding arc X ↔ Z due to Tian’s identifiability [Tian and Pearl, 2002]; Step 2.”
On Pearl’s Hierarchy and the Foundations of Causal Inference (2022, methodology): “To witness, consider We introduce below a construct called confounded component [Tian and Pearl 2002b] to restore and help to make sense of modularity in these models.”
The seven tools of causal inference, with reflections on machine learning (2019, methodology): “Fortunately, efficient and complete algorithms have been developed to decide identifiability and produce Estimands for a variety of counterfactual queries and a variety of data types.(3,30,32) I next provide a bird’s-eye view of seven tasks accomplished through the SCM framework and the tools used i”
Causal and Counterfactual Inference (2018, background): “The results stated in Theorem 1 were developed in several stages over the past 20 years (Pearl, 1993, 1995; Shpitser & Pearl, 2006; Tian & Pearl, 2002).”
Transportability from Multiple Environments with Limited Experiments: Completeness Results (2014, methodology): “There exists an extensive literature concerned with the problem of computability of causal relations from a combination of assumptions and data [21, 22, 7, 13].”
Effects of Treatment on the Treated: Identification and Generalization (2009, background): “Note the difference between this result and the one in [12].”
Do-calculus when the True Graph Is Unknown (2015, methodology): “For example, the entire literature on algorithms applying the do -calculus assumes — generally without further discussion — that the causal graph is known (Tian and Pearl, 2002; Huang and Valtorta, 2006; Shpitser and Pearl, 2006b; Bareinboim and Pearl, 2012).”
Causal diagrams for interference (2014, methodology): “…of causal effects in many settings (Dahlhaus and Eichler, 2003; Didelez, Kreiner and Keiding, 2010; Freedman, 2004; Greenland, Pearl and Robins, 1999; Pearl, 1995, 1997, 2000; Robins, 2003; Tian and Pearl, 2002a; Vansteelandt, 2007) but have not yet been applied to settings with interference.”
On the Testable Implications of Causal Models with Hidden Variables (2002, methodology): “The importance of the c-factors stems from that all c-factors are computable from P(v) [Tian and Pearl, 2002].”
The Causal Foundations of Structural Equation Modeling (2012, methodology): “Each of these functions represents a causal process (or mechanism) that determines the value of the left variable (output) from the values on the right variables (inputs).”
Causal analysis with Chain Event Graphs (2010, background): “Necessary and sufficient conditions for causal identifiability (expressed as functions of the topology of the idle BN) have now been proved for most scenarios [22,35,7,34].”