Causal Effect Identification in LiNGAM Models with Latent Confounders

2024/06/04 by Daniele Tramontano, Tramontano, Daniele, Yaroslav Kivva +7 · 2 citations
Computer Science · #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Methodology (stat.ME)

paper · pdf · doi:10.48550/arxiv.2406.02049

openalex publication_date 2024/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

We study the generic identifiability of causal effects in linear non-Gaussian acyclic models (LiNGAM) with latent variables. We consider the problem in two main settings: When the causal graph is known a priori, and when it is unknown. In both settings, we provide a complete graphical characterization of the identifiable direct or total causal effects among observed variables. Moreover, we propose efficient algorithms to certify the graphical conditions. Finally, we propose an adaptation of the reconstruction independent component analysis (RICA) algorithm that estimates the causal effects from the observational data given the causal graph. Experimental results show the effectiveness of the proposed method in estimating the causal effects.

Cited by

• Trek-Based Parameter Identification for Linear Causal Models With Arbitrarily Structured Latent Variables
• Estimating Treatment Effects with Independent Component Analysis

Related

• Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants
• Parameter identification in linear non-Gaussian causal models under general confounding
• Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables
• Trek-Based Parameter Identification for Linear Causal Models With Arbitrarily Structured Latent Variables
• Discovery of non-gaussian linear causal models using ICA