Uniform consistency in causal inference

By James M. Robins, Richard Scheines, Peter Spirtes, Larry A. Wasserman. 2003

167 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 through a Witness Protection Program (2014, background): “However, there exist distributions faithful to the IV structure but which at finite sample sizes may appear to satisfy the Markov property for the structure W → X → Y ; in practice this can occur at any finite sample size (Robins et al., 2003).”
Estimating High-Dimensional Directed Acyclic Graphs with the PC-Algorithm (2005, neutral): “2 The skeleton of a DAG”
Limitations of individual causal models, causal graphs, and ignorability assumptions, as illustrated by random confounding and design unfaithfulness (2015, background): “[13]; and”
Adjacency-Faithfulness and Conservative Causal Inference (2006, unknown): “…we expect that the CPC algorithm will do particularly better than the PC algorithm when the distribution generated is close-to-unfaithful to the true graph { a situation pointed out by several authors as a major obstacle to reliable causal inference (Robins et al. 2003, Zhang and Spirtes 2003).”
A Theoretical Study of Y Structures for Causal Discovery (2006, background): “…in V , entails the same conditional independence relations over V , and in which there is a (measured or unmeasured) confounder of X and Z , or in which X is not an ancestor of Z (Robins et al., 2003; Spirtes et al., 2000, page 187) that is in the same independence equivalence class as G 1 .”
Detection of Unfaithfulness and Robust Causal Inference (2008, background): “Assuming the CMC and CFC hold of the true population distribution, from which samples are drawn, is there a uniformly consistent procedure to test H0 versus H1? The impossibility result of Robins et al. (2003) does not apply here, because the essential condition for their argument, what Zhang (200”
MAXIMUM LIKELIHOOD FOR SPARSE DIRECTED ACYCLIC GRAPHS (2013, background): “Robins et al. (2003) present refined analyses for causal inference under the view point of uniform consistency as sample size n → ∞.”
For and Against Methodologies: Some Perspectives on Recent Causal and Statistical Inference Debates (2017, background): “This shift away from obsessions with null testing paralleled movements in other 13 When in addition to the causal graph we can assume faithfulness (open paths imply association), the number of logically possible structures is reduced drastically – to the point that a certain limited type of conditio”
Geometry of the faithfulness assumption in causal inference (2012, unknown): “05 47 v3 [ m at h. ST ] 2 2 A pr 2 01 3 The Annals of Statistics 2013, Vol. 41, No. 2, 436–463 DOI: 10.1214/12-AOS1080 c© Institute of Mathematical Statistics, 2013”
Estimating high-dimensional intervention effects from observational data (2008, methodology): “We refer to [28] and [35] for a discussion about pointwise versus uniform consistency of the PC-algorithm.”
Data-driven covariate selection for nonparametric estimation of causal effects (2013, background): “We thus obtain an admissible set (blocking all back-door paths from x to y) as Z = Z′ \ {x}, since to any back-door path from x to y we can concatenate the edge p → x to obtain a path from p to y via x with x being an active collider, and hence any such path must be blocked by Z.”
$\ell_0$-penalized maximum likelihood for sparse directed acyclic graphs (2012, background): “Robins et al. (2003) present reﬁned analyses for causal inference under the view point of uniform consistency as sample size n → ∞ . see There, problematic issues with the so-called faithfulness condition ( Section 1.2) arise, and Zhang and Spirtes (2003) introduce the notion of strong faithfulness…”