Identifiability of total effects from abstractions of time series causal graphs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916615113670656 |
|---|---|
| author | Assaad, Charles K. Devijver, Emilie Gaussier, Eric Gössler, Gregor Meynaoui, Anouar |
| author_facet | Assaad, Charles K. Devijver, Emilie Gaussier, Eric Gössler, Gregor Meynaoui, Anouar |
| contents | We study the problem of identifiability of the total effect of an intervention from observational time series in the situation, common in practice, where one only has access to abstractions of the true causal graph. We consider here two abstractions: the extended summary causal graph, which conflates all lagged causal relations but distinguishes between lagged and instantaneous relations, and the summary causal graph which does not give any indication about the lag between causal relations. We show that the total effect is always identifiable in extended summary causal graphs and provide sufficient conditions for identifiability in summary causal graphs. We furthermore provide adjustment sets allowing to estimate the total effect whenever it is identifiable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_14691 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Identifiability of total effects from abstractions of time series causal graphs Assaad, Charles K. Devijver, Emilie Gaussier, Eric Gössler, Gregor Meynaoui, Anouar Statistics Theory Artificial Intelligence We study the problem of identifiability of the total effect of an intervention from observational time series in the situation, common in practice, where one only has access to abstractions of the true causal graph. We consider here two abstractions: the extended summary causal graph, which conflates all lagged causal relations but distinguishes between lagged and instantaneous relations, and the summary causal graph which does not give any indication about the lag between causal relations. We show that the total effect is always identifiable in extended summary causal graphs and provide sufficient conditions for identifiability in summary causal graphs. We furthermore provide adjustment sets allowing to estimate the total effect whenever it is identifiable. |
| title | Identifiability of total effects from abstractions of time series causal graphs |
| topic | Statistics Theory Artificial Intelligence |
| url | https://arxiv.org/abs/2310.14691 |