Estimation of causal effects using linear non-Gaussian causal models with hidden variables

Authors:
Patrik O. Hoyer;Shohei Shimizu;Antti J. Kerminen;Markus Palviainen
Affiliations:
Helsinki Institute for Information Technology, Department of Computer Science, University of Helsinki, Helsinki, Finland and Learning and Inference Group, The Institute of Statistical Mathematics, ...;Helsinki Institute for Information Technology, Department of Computer Science, University of Helsinki, Helsinki, Finland and Learning and Inference Group, The Institute of Statistical Mathematics, ...;Helsinki Institute for Information Technology, Department of Computer Science, University of Helsinki, Helsinki, Finland and Learning and Inference Group, The Institute of Statistical Mathematics, ...;Helsinki Institute for Information Technology, Department of Computer Science, University of Helsinki, Helsinki, Finland and Learning and Inference Group, The Institute of Statistical Mathematics, ...
Venue:
International Journal of Approximate Reasoning
Year:
2008

Citing 8
Cited 8

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Independent factor analysis

Neural Computation
Causality: models, reasoning, and inference

Causality: models, reasoning, and inference
A Bayesian Method for Causal Modeling and Discovery Under Selection

UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces

Neural Computation
Learning Overcomplete Representations

Neural Computation
Learning the Structure of Linear Latent Variable Models

The Journal of Machine Learning Research
A Linear Non-Gaussian Acyclic Model for Causal Discovery

The Journal of Machine Learning Research

Automatic linear causal relationship identification for financial factor modeling

Expert Systems with Applications: An International Journal
Identifying confounders using additive noise models

UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity

The Journal of Machine Learning Research
Sparse Linear Identifiable Multivariate Modeling

The Journal of Machine Learning Research
DirectLiNGAM: A Direct Method for Learning a Linear Non-Gaussian Structural Equation Model

The Journal of Machine Learning Research
Letters: Joint estimation of linear non-Gaussian acyclic models

Neurocomputing
Discovering unconfounded causal relationships using linear non-gaussian models

JSAI-isAI'10 Proceedings of the 2010 international conference on New Frontiers in Artificial Intelligence
Estimation of causal orders in a linear non-gaussian acyclic model: a method robust against latent confounders

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The task of estimating causal effects from non-experimental data is notoriously difficult and unreliable. Nevertheless, precisely such estimates are commonly required in many fields including economics and social science, where controlled experiments are often impossible. Linear causal models (structural equation models), combined with an implicit normality (Gaussianity) assumption on the data, provide a widely used framework for this task. We have recently described how non-Gaussianity in the data can be exploited for estimating causal effects. In this paper we show that, with non-Gaussian data, causal inference is possible even in the presence of hidden variables (unobserved confounders), even when the existence of such variables is unknown a priori. Thus, we provide a comprehensive and complete framework for the estimation of causal effects between the observed variables in the linear, non-Gaussian domain. Numerical simulations demonstrate the practical implementation of the proposed method, with full Matlab code available for all simulations.