Chain graph models and their causal interpretations

By Steffen L. Lauritzen, Thomas S. Richardson. 2002

314 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Causal inference by using invariant prediction: identification and confidence intervals (2015, background): “We do not touch on the framework of feedback models [Lauritzen and Richardson, 2002, Mooij et al., 2011, Hyttinen et al., 2012, cf.], and it is an open question whether our concept of invariance would provide a useful key for such models as well.”
Counterfactual reasoning and learning systems: the example of computational advertising (2012, background): “Quantities measured when a feedback causal system reaches equilibrium often display conditional independence patterns that cannot be represented with directed acyclic graphs (Lauritzen and Richardson, 2002; Dash, 2003).”
Minimal sufficient causation and directed acyclic graphs (2009, background): “Another direction of further research might involve the incorporation of the AND and OR nodes that arise from sufficient causation structures into other graphical models such as summary graphs [4], MC-graphs [12], chain graph models [2, 6, 14, 15, 16, 23, 34, 42] and ancestral graph models [24].”
Active Learning of Causal Networks with Intervention Experiments and Optimal Designs (2008, methodology): “Chain graphs were introduced as a natural generalization of DAGs to admit more flexible causal interpretation (Lauritzen and Richardson, 2002).”
Formalizing Neurath’s Ship: Approximate Algorithms for Online Causal Learning (2016, methodology): “Another is the chain graph (Lauritzen & Richardson, 2002), in which undirected edges are mixed with directed edges and used to model the equilibria of the cyclic parts of the system.”
Markov properties for mixed graphs (2011, unknown): “However, the independence model induced by m-separation in a chain graph is typically different from any of the other chain graph interpretations; see also [22,25] and [20].”
Instrumental Variables: An Econometrician's Perspective (2014, unknown): “Hernán and Robins (2006) write this average potential outcome as E[lnQdt (Pt = 1)], whereas Lauritzen and Richardson (2002) write it as E[lnQobst ‖ P obst = 1] where the double ‖ implies conditioning by intervention. of market is that the price that is observed, that is, the price at which the fish…”
Graphical causal models and VARs: an empirical assessment of the real business cycles hypothesis (2008, background): “…is referred to Appendix A for a definition of graphs and DAGs— have proved to be useful to represent causal hypotheses and to encode independence and conditional independence constraints implied by those hypotheses (Pearl 2000; Spirtes et al. 2000; Lauritzen 2001; Lauritzen and Richardson 2002).”
Learning linear cyclic causal models with latent variables (2012, methodology): “The equilibrium we describe here corresponds to what Lauritzen and Richardson (2002) called a deterministic equilibrium, since the equilibrium value of x(t) is fully determined given a sample of the disturbances e.”
Causality, mediation and time: a dynamic viewpoint (2012, background): “In fact, the interesting paper by Lauritzen and Richardson (2002) connects the concept of a chain graph (an extension of a DAG allowing for undirected edges) to equilibrium distributions in stochastic processes.”
Modeling Discrete Interventional Data using Directed Cyclic Graphical Models (2009, methodology): “Following §6 of Lauritzen and Richardson (2002), we can consider a Markov chain Monte Carlo method for simulating from a distribution represented with inter- the target of intervention with a simple assignment operator (Strotz and Wold, 1960).”