Estimating causal effects using triplet orderings: scale free graphs and dependence on the node order

Abstract : For many data analysis tasks, obtaining the causal relationships between interacting objects is of crucial interest. Here, the case of modelling causal relationships via causal orderings is considered. Triplet ordering preferences are used to perform Monte Carlo sampling of the posterior causal orderings originating from the analysis of experiments involving observation as well as, usually few, interventions, like knockouts in case of gene expression. The performance of this sampling approach is compared to a previously used sampling via pairwise ordering preference as well as to the sampling of the full posterior distribution. This is performed for artificially generated causal, i.e. directed acyclic graphs (DAGs) with a scale-free structure, i.e. a power-law distribution for the out-degree. The sampling using the triplets ordering turns out to be superior to both other approaches, similar to our previous work, where the less-realistic case of Erdős-R nyi random graphs was considered.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02350429
Contributor : Gregory Nuel <>
Submitted on : Wednesday, November 6, 2019 - 8:19:48 AM
Last modification on : Saturday, November 9, 2019 - 2:15:42 AM

File

Hartmann_2018.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Alexander Hartmann, Gregory Nuel. Estimating causal effects using triplet orderings: scale free graphs and dependence on the node order. Journal of Physics: Conference Series, IOP Publishing, 2018, 1036, pp.012002. ⟨10.1088/1742-6596/1036/1/012002⟩. ⟨hal-02350429⟩

Share

Metrics

Record views

8

Files downloads

14