A Topological Perspective on Causal Inference

07/18/2021
by   Duligur Ibeling, et al.
0

This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs). As an illustration of the framework we prove a topological causal hierarchy theorem, showing that substantive assumption-free causal inference is possible only in a meager set of SCMs. Thanks to a known correspondence between open sets in the weak topology and statistically verifiable hypotheses, our results show that inductive assumptions sufficient to license valid causal inferences are statistically unverifiable in principle. Similar to no-free-lunch theorems for statistical inference, the present results clarify the inevitability of substantial assumptions for causal inference. An additional benefit of our topological approach is that it easily accommodates SCMs with infinitely many variables. We finally suggest that the framework may be helpful for the positive project of exploring and assessing alternative causal-inductive assumptions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/04/2018

Causal programming: inference with structural causal models as finding instances of a relation

This paper proposes a causal inference relation and causal programming a...
research
06/02/2020

The role of exchangeability in causal inference

The notion of exchangeability has been recognized in the causal inferenc...
research
11/09/2020

DoWhy: An End-to-End Library for Causal Inference

In addition to efficient statistical estimators of a treatment's effect,...
research
02/10/2023

Causal Inference out of Control: Estimating the Steerability of Consumption

Regulators and academics are increasingly interested in the causal effec...
research
10/17/2019

Comment: Reflections on the Deconfounder

The aim of this comment (set to appear in a formal discussion in JASA) i...
research
07/11/2022

Positivity: Identifiability and Estimability

Positivity, the assumption that every unique combination of confounding ...
research
04/08/2020

DAG With Omitted Objects Displayed (DAGWOOD): A framework for revealing causal assumptions in DAGs

Directed acyclic graphs (DAGs) are frequently used in epidemiology as a ...

Please sign up or login with your details

Forgot password? Click here to reset