Causal discovery of linear acyclic models with arbitrary distributions

Abstract

An important task in data analysis is the discovery of causal relationships between observed variables. For continuous-valued data, linear acyclic causal models are commonly used to model the data-generating process, and the inference of such models is a well-studied problem. However, existing methods have significant limitations. Methods based on conditional independencies (Spirtes et al. 1993; Pearl 2000) cannot distinguish between independence-equivalent models, whereas approaches purely based on Independent Component Analysis (Shimizu et al. 2006) are inapplicable to data which is partially Gaussian. In this paper, we generalize and combine the two approaches, to yield a method able to learn the model structure in many cases for which the previous methods provide answers that are either incorrect or are not as informative as possible. We give exact graphical conditions for when two distinct models represent the same family of distributions, and empirically demonstrate the power of our method through thorough simulations.

arXiv commentAppears in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI2008)

References in corpus (1)

• Causal Inference and Causal Explanation with Background Knowledge

Cited by in corpus (12)

• Causal interpretation rules for encoding and decoding models in neuroimaging
• Graphical Criteria for Efficient Total Effect Estimation via Adjustment in Causal Linear Models
• Discovering Cyclic Causal Models by Independent Components Analysis
• Bayesian Discovery of Linear Acyclic Causal Models
• Efficient adjustment sets for population average treatment effect estimation in non-parametric causal graphical models
• Efficient least squares for estimating total effects under linearity and causal sufficiency
• Higher-order least squares: assessing partial goodness of fit of linear causal models
• Identifying causal effects in maximally oriented partially directed acyclic graphs
• Combining Linear Non-Gaussian Acyclic Model with Logistic Regression Model for Estimating Causal Structure from Mixed Continuous and Discrete Data
• Bayesian estimation of possible causal direction in the presence of latent confounders using a linear non-Gaussian acyclic structural equation model with individual-specific effects
• Minimal enumeration of all possible total effects in a Markov equivalence class
• How do governments determine policy priorities? Studying development strategies through spillover networks