Causal Inference on Process Graphs, Part II: Causal Structure and Effect Identification

TL;DR

This paper develops methods for causal discovery and effect estimation in linear SVAR processes using spectral density analysis, enabling identification of causal structures and effects even with latent confounders.

Contribution

It introduces algebraic constraints on spectral density for causal discovery and a rational identifiability concept for causal effects in the frequency domain.

Findings

Spectral density constraints can recover process graph structure.

Graphical criteria assess causal effect identifiability with latent confounders.

Method extends causal inference to frequency domain analysis.

Abstract

A structural vector autoregressive (SVAR) process is a linear causal model for variables that evolve over a discrete set of time points and between which there may be lagged and instantaneous effects. The qualitative causal structure of an SVAR process can be represented by its finite and directed process graph, in which a directed link connects two processes whenever there is a lagged or instantaneous effect between them. At the process graph level, the causal structure of SVAR processes is compactly parameterised in the frequency domain. In this paper, we consider the problem of causal discovery and causal effect estimation from the spectral density, the frequency domain analogue of the auto covariance, of the SVAR process. Causal discovery concerns the recovery of the process graph and causal effect estimation concerns the identification and estimation of causal effects in the frequency domain. We show that information about the process graph, in terms of $d$- and $t$-separation statements, can be identified by verifying algebraic constraints on the spectral density. Furthermore, we introduce a notion of rational identifiability for frequency causal effects that may be confounded by exogenous latent processes, and show that the recent graphical latent factor half-trek criterion can be used on the process graph to assess whether a given (confounded) effect can be identified by rational operations on the entries of the spectral density.