Meaningful Causal Aggregation and Paradoxical Confounding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Yuchen, Budhathoki, Kailash, Kuebler, Jonas, Janzing, Dominik
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913239119429632
author Zhu, Yuchen
Budhathoki, Kailash
Kuebler, Jonas
Janzing, Dominik
author_facet Zhu, Yuchen
Budhathoki, Kailash
Kuebler, Jonas
Janzing, Dominik
contents In aggregated variables the impact of interventions is typically ill-defined because different micro-realizations of the same macro-intervention can result in different changes of downstream macro-variables. We show that this ill-definedness of causality on aggregated variables can turn unconfounded causal relations into confounded ones and vice versa, depending on the respective micro-realization. We argue that it is practically infeasible to only use aggregated causal systems when we are free from this ill-definedness. Instead, we need to accept that macro causal relations are typically defined only with reference to the micro states. On the positive side, we show that cause-effect relations can be aggregated when the macro interventions are such that the distribution of micro states is the same as in the observational distribution; we term this natural macro interventions. We also discuss generalizations of this observation.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11625
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Meaningful Causal Aggregation and Paradoxical Confounding
Zhu, Yuchen
Budhathoki, Kailash
Kuebler, Jonas
Janzing, Dominik
Artificial Intelligence
Machine Learning
In aggregated variables the impact of interventions is typically ill-defined because different micro-realizations of the same macro-intervention can result in different changes of downstream macro-variables. We show that this ill-definedness of causality on aggregated variables can turn unconfounded causal relations into confounded ones and vice versa, depending on the respective micro-realization. We argue that it is practically infeasible to only use aggregated causal systems when we are free from this ill-definedness. Instead, we need to accept that macro causal relations are typically defined only with reference to the micro states. On the positive side, we show that cause-effect relations can be aggregated when the macro interventions are such that the distribution of micro states is the same as in the observational distribution; we term this natural macro interventions. We also discuss generalizations of this observation.
title Meaningful Causal Aggregation and Paradoxical Confounding
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2304.11625