Filters








2,099 Hits in 6.7 sec

On the completeness of orientation rules for causal discovery in the presence of latent confounders and selection bias

Jiji Zhang
2008 Artificial Intelligence  
Causal discovery becomes especially challenging when the possibility of latent confounding and/or selection bias is not assumed away.  ...  Based on the machinery of ancestral graphs, there is a provably sound causal discovery algorithm, known as the FCI algorithm, that allows the possibility of latent confounders and selection bias.  ...  The FCI algorithm and arrowhead completeness The MAG representation gives us a relatively tractable problem of causal discovery in the presence of latent confounders and selection variables: to infer features  ... 
doi:10.1016/j.artint.2008.08.001 fatcat:gx4b7so26fhuler2oxtcvchwgq

Towards Robust and Versatile Causal Discovery for Business Applications

Giorgos Borboudakis, Ioannis Tsamardinos
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
These include (a) ability to accept prior causal knowledge (e.g., taking senior driving courses improves driving skills), (b) admitting the presence of latent confounding factors, (c) admitting the possibility  ...  Causal discovery algorithms can induce some of the causal relations from the data, commonly in the form of a causal network such as a causal Bayesian network.  ...  We would like to thank the anonymous reviewers for their comments. This work was funded by the ERC Consolidator Grant No 617393 CAUSALPATH.  ... 
doi:10.1145/2939672.2939872 dblp:conf/kdd/BorboudakisT16 fatcat:6sjw5zcgjzc2bfqo3hh66xbwze

Local Constraint-Based Causal Discovery under Selection Bias [article]

Philip Versteeg, Cheng Zhang, Joris M. Mooij
2022 arXiv   pre-print
While the seminal FCI algorithm is sound and complete in this setup, no criterion for the causal interpretation of its output under selection bias is presently known.  ...  We consider the problem of discovering causal relations from independence constraints selection bias in addition to confounding is present.  ...  Acknowledgments PV and JMM are supported by NWO, the Netherlands Organization for Scientific Research (VIDI grant 639.072.410).  ... 
arXiv:2203.01848v1 fatcat:bc2rotbpf5goxmnzqwtmmev2rq

Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias [article]

Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz, Gal Novik
2022 arXiv   pre-print
We present a sound and complete algorithm, called iterative causal discovery (ICD), for recovering causal graphs in the presence of latent confounders and selection bias.  ...  ICD relies on the causal Markov and faithfulness assumptions and recovers the equivalence class of the underlying causal graph.  ...  Related Work Causal discovery in the potential presence of latent confounders and selection bias requires placing additional assumptions.  ... 
arXiv:2111.04095v2 fatcat:b7qnlu4bsbbv5jhpinkn7qcwcq

On the Completeness of Causal Discovery in the Presence of Latent Confounding with Tiered Background Knowledge

Bryan Andrews
2020 International Conference on Artificial Intelligence and Statistics  
In this paper, we define tiered background knowledge and show that FCI is sound and complete with the incorporation of this knowledge.  ...  The discovery of causal relationships is a core part of scientific research.  ...  The content of this paper is solely the responsibility of the authors and does not necessarily represent the official views of these funding agencies.  ... 
dblp:conf/aistats/Andrews20 fatcat:mu76folhcrb23k4xj3mtehyvlm

A Characterization of Markov Equivalence Classes for Directed Acyclic Graphs with Latent Variables [article]

Jiji Zhang
2012 arXiv   pre-print
We end up with a set of orientation rules sound and complete for identifying commonalities across a Markov equivalence class of MAGs, which is particularly useful for causal inference.  ...  Meek (1995) characterizes Markov equivalence classes for DAGs (with no latent variables) by presenting a set of orientation rules that can correctly identify all arrow orientations shared by all DAGs in  ...  Acknowledgement I thank Peter Spirtes and Thomas Richardson for checking the proofs in Zhang (2006) .  ... 
arXiv:1206.5282v1 fatcat:abwtqieirvby5onel5w2wtspee

Constraint-Based Causal Discovery using Partial Ancestral Graphs in the presence of Cycles [article]

Joris M. Mooij, Tom Claassen
2020 arXiv   pre-print
and absence of causal relations, (ii) the presence and absence of direct causal relations, (iii) the absence of confounders, and (iv) the absence of specific cycles in the causal graph of the SCM.  ...  More specifically, we prove that for observational data generated by a simple and σ-faithful Structural Causal Model (SCM), FCI is sound and complete, and can be used to consistently estimate (i) the presence  ...  Acknowledgements We are indebted to Jiji Zhang for contributing the proof of Proposition 13. We thank the reviewers for their constructive feedback that helped us improve this paper.  ... 
arXiv:2005.00610v2 fatcat:crgpwy4vnbg5nlanm4q7tnhv5y

A Constraint-Based Algorithm For Causal Discovery with Cycles, Latent Variables and Selection Bias [article]

Eric V. Strobl
2018 arXiv   pre-print
No constraint-based causal discovery algorithm can currently handle cycles, latent variables and selection bias (CLS) simultaneously.  ...  Causal processes in nature may contain cycles, and real datasets may violate causal sufficiency as well as contain selection bias.  ...  On the completeness of orientation rules for causal discovery in the presence of latent confounders and selection bias. Artif. Intell., 172(16-17): 1873-1896, Nov. 2008.  ... 
arXiv:1805.02087v1 fatcat:ob3anhnmg5e73lscxhjwbjok4i

A Logical Characterization of Constraint-Based Causal Discovery [article]

Tom Claassen, Tom Heskes
2012 arXiv   pre-print
It is both sound and complete, in the sense that all invariant features of the corresponding partial ancestral graph (PAG) are identified, even in the presence of latent variables and selection bias.  ...  We present a novel approach to constraint-based causal discovery, that takes the form of straightforward logical inference, applied to a list of simple, logical statements about causal relations that are  ...  Acknowledgement This research was supported by VICI grant 639.023.604 from the Netherlands Organization for Scientific Research (NWO).  ... 
arXiv:1202.3711v1 fatcat:5tk2k2bzxrfktcqu6iztguaj4m

Review of Causal Discovery Methods Based on Graphical Models

Clark Glymour, Kun Zhang, Peter Spirtes
2019 Frontiers in Genetics  
This paper aims to give a introduction to and a brief review of the computational methods for causal discovery that were developed in the past three decades, including constraint-based and score-based  ...  A fundamental task in various disciplines of science, including biology, is to find underlying causal relations and make use of them.  ...  AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication.  ... 
doi:10.3389/fgene.2019.00524 pmid:31214249 pmcid:PMC6558187 fatcat:q2ruix27tjcc3b4oze4y7223by

Data-Driven Causal Effect Estimation Based on Graphical Causal Modelling: A Survey [article]

Debo Cheng and Jiuyong Li and Lin Liu, Jixue Liu, Thuc Duy Le
2022 arXiv   pre-print
In many fields of scientific research and real-world applications, unbiased estimation of causal effects from non-experimental data is crucial for understanding the mechanism underlying the data and for  ...  In this survey, we review the methods and focus on the challenges the data-driven methods face. We discuss the assumptions, strengths and limitations of the data-driven methods.  ...  It is critical to remove the confounding bias for obtaining unbiased causal effect estimation even in the presence of latent variables.  ... 
arXiv:2208.09590v1 fatcat:corkuokpungcrjsaiy3mhj6iqy

Learning Sparse Causal Models is not NP-hard [article]

Tom Claassen, Joris Mooij, Tom Heskes
2013 arXiv   pre-print
This paper shows that causal model discovery is not an NP-hard problem, in the sense that for sparse graphs bounded by node degree k the sound and complete causal model can be obtained in worst case order  ...  N^2(k+2) independence tests, even when latent variables and selection bias may be present.  ...  However, in this paper we show that causal model discovery in sparse graphs is in fact not an NP-hard problem, even in the presence of latent confounders and/or selection bias.  ... 
arXiv:1309.6824v1 fatcat:li2f4txr6zaftenweqyb4igf5a

Comparison of strategies for scalable causal discovery of latent variable models from mixed data

Vineet K. Raghu, Joseph D. Ramsey, Alison Morris, Dimitrios V. Manatakis, Peter Sprites, Panos K. Chrysanthis, Clark Glymour, Panayiotis V. Benos
2018 International Journal of Data Science and Analytics  
In this paper, we present a comparative study that addresses this problem by comparing the accuracy and efficiency of different strategies in large, mixed datasets with latent confounders.  ...  We demonstrate that these methods significantly outperform the state of the art in the field by achieving both accurate edge orientations and tractable running time in simulation experiments on datasets  ...  Research reported in this publication was supported by the National Institutes of Health under Award Number R01LM012087 (to PVB and CG) and T32CA082084 (to VKR).  ... 
doi:10.1007/s41060-018-0104-3 pmid:30148202 pmcid:PMC6096780 dblp:journals/ijdsa/RaghuRMMSCGB18 fatcat:cda5hrilarb5polxrtwm3yadwe

Joint Causal Inference from Multiple Contexts [article]

Joris M. Mooij, Sara Magliacane, Tom Claassen
2020 arXiv   pre-print
We evaluate different JCI implementations on synthetic data and on flow cytometry protein expression data and conclude that JCI implementations can considerably outperform state-of-the-art causal discovery  ...  The gold standard for discovering causal relations is by means of experimentation.  ...  Acknowledgments We thank Thijs van Ommen for useful discussions and the reviewers and editor for their constructive comments.  ... 
arXiv:1611.10351v6 fatcat:bgay5pzo4ba63i6sul4wjirro4

Marginal Causal Consistency in Constraint-based Causal Learning

Anna Roumpelaki, Giorgos Borboudakis, Sofia Triantafillou, Ioannis Tsamardinos
2016 Conference on Uncertainty in Artificial Intelligence  
Maximal Ancestral Graphs (MAGs) are probabilistic graphical models that can model the distribution and causal properties of a set of variables in the presence of latent confounders.  ...  In principle, the causal relationships identified by FCI on a data set D measuring a set of variables V should not conflict the output of FCI on marginal data sets including only subsets of V.  ...  Acknowledgments We would like to thank the anonymous reviewers for their comments, particularly reviewer 2 who helped us identify a problem in the simulations in the submitted version of this paper.  ... 
dblp:conf/uai/RoumpelakiBTT16 fatcat:7mif3ccjzvay7nx55ayxta2qam
« Previous Showing results 1 — 15 out of 2,099 results