Fast Restricted Causal Inference

TL;DR

This paper introduces a new, faster algorithm for causal inference that maintains correctness under reliable statistical tests, improving upon existing algorithms like FCI in handling hidden variables.

Contribution

It presents a novel algorithm that accelerates the CI process while ensuring no false independencies are introduced, unlike previous methods such as FCI.

Findings

The new algorithm is faster than existing methods.

It guarantees no false independencies with reliable tests.

It is applicable to models with hidden variables.

Abstract

Hidden variables are well known sources of disturbance when recovering belief networks from data based only on measurable variables. Hence models assuming existence of hidden variables are under development. This paper presents a new algorithm "accelerating" the known CI algorithm of Spirtes, Glymour and Scheines {Spirtes:93}. We prove that this algorithm does not produces (conditional) independencies not present in the data if statistical independence test is reliable. This result is to be considered as non-trivial since e.g. the same claim fails to be true for FCI algorithm, another "accelerator" of CI, developed in {Spirtes:93}.