Complete Identification Methods for the Causal Hierarchy

By Ilya Shpitser, Judea Pearl. 2008

288 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Causal Inference & Discovery

How researchers see this paper

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

In Artificial Intelligence

In Causal Inference & Discovery

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].”
Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms (2018, background): “Shpitser and Pearl (2008) develop a causal hierarchy consisting of three layers of increasing complexity: association, intervention, and counterfactual.”
Challenges of Using Text Classifiers for Causal Inference (2018, background): “Identifiability is a primary concern of causal inference (Shpitser and Pearl, 2008).”
Foundations of structural causal models with cycles and latent variables (2016, background): “These different equivalence relations formalize the different levels of abstraction in the so-called causal hierarchy [50, 64].”
TRYGVE HAAVELMO AND THE EMERGENCE OF CAUSAL CALCULUS (2014, unknown): “Given any such model, an effective algorithm exists that decides if the causal effect of any subset of variables on another is identifiable and, if so, the algorithm delivers the correct estimand (Shpitser and Pearl, 2008).”
Causal Inference Using Graphical Models with the R Package pcalg (2012, background): “Shpitser and Pearl (2008) restructured the rules of “do-calculus” into algorithmic form and showed that they are complete in a sense that, if the algorithm doesn’t ﬁnd a transformation, there exists none.”
PC-Fairness: A Unified Framework for Measuring Causality-based Fairness (2019, background): “Unfortunately, in many situations these causal effects are in general unidentiﬁable, referred to as unidentiﬁable situations [12].”
The Causal Mediation Formula—A Guide to the Assessment of Pathways and Mechanisms (2012, methodology): “4A complete set of techniques is now available for neutralizing error dependencies, whenever possible, both by covariate adjustment and through the use of instrumental variables (Pearl 2009; Shpitser and Pearl 2008; Tian and Shpitser 2010).”
EIGHT MYTHS ABOUT CAUSALITY AND STRUCTURAL EQUATION MODELS (2013, unknown): “Finally, a complete graphical criterion has been derived that enables a researcher to inspect the graph and write down the estimable expression, whenever such expressions exist (Shpitser and Pearl 2008a).”
Nested Markov Properties for Acyclic Directed Mixed Graphs (2012, background): “This impliesD andD satisfy the definition of a hedge for p(xY | doG(H∪V )(xA∗)) = p(xY | doG(H∪V )(xA)) in G(V ) (Shpitser and Pearl, 2007).”
The seven tools of causal inference, with reflections on machine learning (2019, methodology): “For models where the backdoor criterion does not hold, a symbolic engine is available, called “do-calculus,” that predicts the effect of policy interventions whenever feasible and exits with failure whenever predictions cannot be ascertained on the basis of the specified assumptions.(3,17,30,32) Too”
CAUSAL INFERENCE WITH A GRAPHICAL HIERARCHY OF INTERVENTIONS (2014, background): “The synthesis of potential outcomes and graphs has been instrumental in much of the recent work on identification of various types of causal parameters such as total effects [16, 29, 21, 22, 23], and mediated effects [7, 1, 20].”
Interpretation and identification of causal mediation. (2014, unknown): “It is important to note that the problem of deciding whether such reduction exists has been fully solved using the do-calculus (Shpitser and Pearl, 2008; Tian and Shpitser, 2010).”
Missing Data as a Causal and Probabilistic Problem (2015, background): “In fact, the relationship between our algorithm and MAR is not unlike the relationship between the ID algorithm for identification of causal effects [22, 18, 19], and the conditional ignorability assumption in causal inference [13].”
The explanation game: a formal framework for interpretable machine learning (2020, unknown): “…formulations have been proposed for such adjustments (Galles and Pearl 1995; Pearl 1995; Robins 1997), we follow Tian and Pearl (2002), who provide a provably sound and complete set of causal identifiability conditions for semi-Markovian models (Huang and Valtorta 2008; Shpitser and Pearl 2008).”