Causal Effect Identification in Heterogeneous Environments from Higher-Order Moments

TL;DR

This paper develops a method to identify causal effects in heterogeneous environments using higher-order moments, assuming certain invariance conditions, and introduces algorithms for estimation and parameter variation detection.

Contribution

It provides a moment-based algorithm for causal effect estimation across environments with limited varying parameters and characterizes conditions for identifiability.

Findings

Causal effect is identifiable when the target remains invariant across environments.

The proposed algorithm accurately estimates causal effects with a single varying parameter.

Identifiability fails if multiple parameters vary simultaneously.

Abstract

We investigate the estimation of the causal effect of a treatment variable on an outcome in the presence of a latent confounder. We first show that the causal effect is identifiable under certain conditions when data is available from multiple environments, provided that the target causal effect remains invariant across these environments. Secondly, we propose a moment-based algorithm for estimating the causal effect as long as only a single parameter of the data-generating mechanism varies across environments -- whether it be the exogenous noise distribution or the causal relationship between two variables. Conversely, we prove that identifiability is lost if both exogenous noise distributions of both the latent and treatment variables vary across environments. Finally, we propose a procedure to identify which parameter of the data-generating mechanism has varied across the environments and evaluate the performance of our proposed methods through experiments on synthetic data.