Causal Effect Identification in LiNGAM Models with Latent Confounders

TL;DR

This paper investigates the identifiability of causal effects in LiNGAM models with latent confounders, providing graphical characterizations, algorithms, and an adapted ICA method to estimate causal effects from observational data.

Contribution

It offers a complete graphical characterization of identifiable causal effects in LiNGAM with latent variables and introduces algorithms and an adapted ICA method for causal effect estimation.

Findings

Algorithms effectively certify graphical conditions for identifiability.

The adapted RICA algorithm accurately estimates causal effects from observational data.

Experimental results demonstrate the method's effectiveness in causal effect estimation.

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.