Author:
Genin Konstantin,Mayo-Wilson Conor
Abstract
AbstractExisting causal discovery algorithms are often evaluated using two success criteria, one that is typically unachievable and the other which is too weak for practical purposes. The unachievable criterion—uniform consistency—requires that a discovery algorithm identify the correct causal structure at a known sample size. The weak but achievable criterion— pointwise consistency—requires only that one identify the correct causal structure in the limit. We investigate two intermediate success criteria—decidability and progressive solvability—that are stricter than mere consistency but weaker than uniform consistency. To do so, we review several topological theorems characterizing which discovery problems are decidable and/or progressively solvable. These theorems apply to any problem of statistical model selection, but in this paper, we apply the theorems only to selection of causal models. We show, under several common modeling assumptions, that there is no uniformly consistent procedure for identifying the direction of a causal edge, but there are statistical decision procedures and progressive solutions. We focus on linear models in which the error terms are either non-Gaussian or contain no Gaussian components; the latter modeling assumption is novel to this paper. We focus especially on which success criteria remain feasible when confounders are present.
Funder
German Research Foundation
Eberhard Karls Universität Tübingen
Publisher
Springer Science and Business Media LLC
Subject
Applied Mathematics,Clinical Psychology,Experimental and Cognitive Psychology,Analysis
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献