Causal Inference in the Presence of Latent Variables and Selection Bias

Abstract

We show that there is a general, informative and reliable procedure for discovering causal relations when, for all the investigator knows, both latent variables and selection bias may be at work. Given information about conditional independence and dependence relations between measured variables, even when latent variables and selection bias may be present, there are sufficient conditions for reliably concluding that there is a causal path from one variable to another, and sufficient conditions for reliably concluding when no such causal path exists.

Appears in Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence (UAI1995)

References in corpus (1)

• Strong Completeness and Faithfulness in Bayesian Networks

Cited by in corpus (14)

• CausPref: Causal Preference Learning for Out-of-Distribution Recommendation
• A Bayesian Method for Causal Modeling and Discovery Under Selection
• Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs
• Comparative Benchmarking of Causal Discovery Techniques
• DAG-WGAN: Causal Structure Learning With Wasserstein Generative Adversarial Networks
• A review of some recent advances in causal inference
• Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
• Recovering the Graph Underlying Networked Dynamical Systems under Partial Observability: A Deep Learning Approach
• Learning latent causal graphs via mixture oracles
• Towards Robust Relational Causal Discovery
• Noisy-OR Models with Latent Confounding
• Identification of Latent Variables From Graphical Model Residuals
• Causality Learning With Wasserstein Generative Adversarial Networks
• Causality and Generalizability: Identifiability and Learning Methods