Robust Causal Structure Learning with Some Hidden Variables

DOI10.1111/RSSB.12315zbMATH Open1420.62361arXiv1708.01151OpenAlexW2886399985WikidataQ128296378 ScholiaQ128296378MaRDI QIDQ5234409FDOQ5234409

Authors: Benjamin Frot, Preetam Nandy, Marloes H. Maathuis 

Publication date: 26 September 2019

Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Abstract: We introduce a new method to estimate the Markov equivalence class of a directed acyclic graph (DAG) in the presence of hidden variables, in settings where the underlying DAG among the observed variables is sparse, and there are a few hidden variables that have a direct effect on many of the observed ones. Building on the so-called low rank plus sparse framework, we suggest a two-stage approach which first removes the effect of the hidden variables, and then estimates the Markov equivalence class of the underlying DAG under the assumption that there are no remaining hidden variables. This approach is consistent in certain high-dimensional regimes and performs favourably when compared to the state of the art, both in terms of graphical structure recovery and total causal effect estimation.

Full work available at URL: https://arxiv.org/abs/1708.01151

Recommendations

• Causal structure learning: a combinatorial perspective
• Causal Graphical Models with Latent Variables: Learning and Inference
• Causal Graphical Models with Latent Variables: Learning and Inference
• Causal inference in models with hidden variables and selection bias
• scientific article; zbMATH DE number 1966533
• Identification in causal models with hidden variables
• Semiparametric Bayesian doubly robust causal estimation
• Estimating causal structure using conditional DAG models
• Causal Structural Learning on MPHIA Individual Dataset

zbMATH Keywords

causalityconfoundingdirected acyclic graphsstructured sparsitycausal structure learninghigh dimensional consistency

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Markov processes: estimation; hidden Markov models (62M05) Applications of graph theory (05C90)

Cites Work

• Order-independent constraint-based causal structure learning
• Causation, prediction, and search
• The Adaptive Lasso and Its Oracle Properties
• Title not available (Why is that?)
• A characterization of Markov equivalence classes for acyclic digraphs
• Robust principal component analysis?
• Estimating high-dimensional directed acyclic graphs with the PC-algorithm
• Title not available (Why is that?)
• 10.1162/153244302760200696
• Title not available (Why is that?)
• The max-min hill-climbing Bayesian network structure learning algorithm
• Latent variable graphical model selection via convex optimization
• Causality. Models, reasoning, and inference
• Estimating high-dimensional intervention effects from observational data
• Ancestral graph Markov models.
• Estimating the effect of joint interventions from observational data in sparse high-dimensional settings
• Adaptive estimation of the copula correlation matrix for semiparametric elliptical copulas
• A Quadratically Convergent Newton Method for Computing the Nearest Correlation Matrix
• Title not available (Why is that?)
• Rank-Sparsity Incoherence for Matrix Decomposition
• Learning high-dimensional directed acyclic graphs with latent and selection variables
• Causal inference in statistics: an overview
• Markov equivalence for ancestral graphs
• Title not available (Why is that?)
• PC algorithm for nonparanormal graphical models
• On the completeness of orientation rules for causal discovery in the presence of latent confounders and selection bias
• Statistical analysis of latent generalized correlation matrix estimation in transelliptical distribution
• Alternating Direction Methods for Latent Variable Gaussian Graphical Model Selection
• Learning the structure of linear latent variable models
• Estimating bounds on causal effects in high-dimensional and possibly confounded systems
• Graphical model selection for Gaussian conditional random fields in the presence of latent variables
• High-dimensional consistency in score-based and hybrid structure learning

Cited In (10)

• Nonlinear Causal Discovery with Confounders
• Causal Dantzig: fast inference in linear structural equation models with hidden variables under additive interventions
• Bayesian sample size determination for causal discovery
• The blessings of multiple causes
• Title not available (Why is that?)
• Discovery and Inference of a Causal Network with Hidden Confounding
• Causal structure learning: a combinatorial perspective
• Distributional equivalence and structure learning for bow-free acyclic path diagrams
• Streaming feature-based causal structure learning algorithm with symmetrical uncertainty
• Bayesian inference of causal effects from observational data in Gaussian graphical models

Uses Software

• pcalg
• TETRAD

This page was built for publication: Robust Causal Structure Learning with Some Hidden Variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5234409)