Too Fast Causal Inference under Causal Insufficiency

TL;DR

This paper critically analyzes the Fast Causal Inference (FCI) algorithm, demonstrating its errors in complex cases due to temporary non-real links, and proposes a remedy to improve its reliability in causal inference with latent variables.

Contribution

The paper identifies fundamental flaws in the FCI algorithm for causal inference under causal insufficiency and proposes a correction to address these issues.

Findings

The FCI algorithm is erroneous in complex dependency structures.

Temporary non-real links can lead to incorrect causal conclusions.

A proposed remedy improves the algorithm's correctness.

Abstract

Causally insufficient structures (models with latent or hidden variables, or with confounding etc.) of joint probability distributions have been subject of intense study not only in statistics, but also in various AI systems. In AI, belief networks, being representations of joint probability distribution with an underlying directed acyclic graph structure, are paid special attention due to the fact that efficient reasoning (uncertainty propagation) methods have been developed for belief network structures. Algorithms have been therefore developed to acquire the belief network structure from data. As artifacts due to variable hiding negatively influence the performance of derived belief networks, models with latent variables have been studied and several algorithms for learning belief network structure under causal insufficiency have also been developed. Regrettably, some of them are known already to be erroneous (e.g. IC algorithm of [Pearl:Verma:91]. This paper is devoted to another algorithm, the Fast Causal Inference (FCI) Algorithm of [Spirtes:93]. It is proven by a specially constructed example that this algorithm, as it stands in [Spirtes:93], is also erroneous. Fundamental reason for failure of this algorithm is the temporary introduction of non-real links between nodes of the network with the intention of later removal. While for trivial dependency structures these non-real links may be actually removed, this may not be the case for complex ones, e.g. for the case described in this paper. A remedy of this failure is proposed.