Salvato in:
Dettagli Bibliografici
Autori principali: Yvernes, Clément, Assaad, Charles K., Devijver, Emilie, Gaussier, Eric
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.14862
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916797502980096
author Yvernes, Clément
Assaad, Charles K.
Devijver, Emilie
Gaussier, Eric
author_facet Yvernes, Clément
Assaad, Charles K.
Devijver, Emilie
Gaussier, Eric
contents The identifiability problem for interventions aims at assessing whether the total effect of some given interventions can be written with a do-free formula, and thus be computed from observational data only. We study this problem, considering multiple interventions and multiple effects, in the context of time series when only abstractions of the true causal graph in the form of summary causal graphs are available. We focus in this study on identifiability by a common backdoor set, and establish, for time series with and without consistency throughout time, conditions under which such a set exists. We also provide algorithms of limited complexity to decide whether the problem is identifiable or not.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14862
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Identifiability by common backdoor in summary causal graphs of time series
Yvernes, Clément
Assaad, Charles K.
Devijver, Emilie
Gaussier, Eric
Statistics Theory
Artificial Intelligence
The identifiability problem for interventions aims at assessing whether the total effect of some given interventions can be written with a do-free formula, and thus be computed from observational data only. We study this problem, considering multiple interventions and multiple effects, in the context of time series when only abstractions of the true causal graph in the form of summary causal graphs are available. We focus in this study on identifiability by a common backdoor set, and establish, for time series with and without consistency throughout time, conditions under which such a set exists. We also provide algorithms of limited complexity to decide whether the problem is identifiable or not.
title Identifiability by common backdoor in summary causal graphs of time series
topic Statistics Theory
Artificial Intelligence
url https://arxiv.org/abs/2506.14862