Conditional Adjustment in a Markov Equivalence Class

Sara LaPlante, Emilija Perkovic
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:2782-2790, 2024.

Abstract

We consider the problem of identifying a conditional causal effect through covariate adjustment. We focus on the setting where the causal graph is known up to one of two types of graphs: a maximally oriented partially directed acyclic graph (MPDAG) or a partial ancestral graph (PAG). Both MPDAGs and PAGs represent equivalence classes of possible underlying causal models. After defining adjustment sets in this setting, we provide a necessary and sufficient graphical criterion – the conditional adjustment criterion – for finding these sets under conditioning on variables unaffected by treatment. We further provide explicit sets from the graph that satisfy the conditional adjustment criterion, and therefore, can be used as adjustment sets for conditional causal effect identification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-laplante24a, title = {Conditional Adjustment in a {M}arkov Equivalence Class}, author = {LaPlante, Sara and Perkovic, Emilija}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {2782--2790}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/laplante24a/laplante24a.pdf}, url = {https://proceedings.mlr.press/v238/laplante24a.html}, abstract = {We consider the problem of identifying a conditional causal effect through covariate adjustment. We focus on the setting where the causal graph is known up to one of two types of graphs: a maximally oriented partially directed acyclic graph (MPDAG) or a partial ancestral graph (PAG). Both MPDAGs and PAGs represent equivalence classes of possible underlying causal models. After defining adjustment sets in this setting, we provide a necessary and sufficient graphical criterion – the conditional adjustment criterion – for finding these sets under conditioning on variables unaffected by treatment. We further provide explicit sets from the graph that satisfy the conditional adjustment criterion, and therefore, can be used as adjustment sets for conditional causal effect identification.} }
Endnote
%0 Conference Paper %T Conditional Adjustment in a Markov Equivalence Class %A Sara LaPlante %A Emilija Perkovic %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-laplante24a %I PMLR %P 2782--2790 %U https://proceedings.mlr.press/v238/laplante24a.html %V 238 %X We consider the problem of identifying a conditional causal effect through covariate adjustment. We focus on the setting where the causal graph is known up to one of two types of graphs: a maximally oriented partially directed acyclic graph (MPDAG) or a partial ancestral graph (PAG). Both MPDAGs and PAGs represent equivalence classes of possible underlying causal models. After defining adjustment sets in this setting, we provide a necessary and sufficient graphical criterion – the conditional adjustment criterion – for finding these sets under conditioning on variables unaffected by treatment. We further provide explicit sets from the graph that satisfy the conditional adjustment criterion, and therefore, can be used as adjustment sets for conditional causal effect identification.
APA
LaPlante, S. & Perkovic, E.. (2024). Conditional Adjustment in a Markov Equivalence Class. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:2782-2790 Available from https://proceedings.mlr.press/v238/laplante24a.html.

Related Material