Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge
Abhin Shah, Karthikeyan Shanmugam, Kartik Ahuja
Abstract
Treatment effect estimation from observational data is a fundamental problem in causal inference. There are two very different schools of thought that have tackled this problem. On the one hand, the Pearlian framework commonly assumes structural knowledge (provided by an expert) in the form of directed acyclic graphs and provides graphical criteria such as the back-door criterion to identify the valid adjustment sets. On the other hand, the potential outcomes (PO) framework commonly assumes that all the observed features satisfy ignorability (i.e., no hidden confounding), which in general is untestable. In prior works that attempted to bridge these frameworks, there is an observational criteria to identify an
BibTeX
@InProceedings{pmlr-v151-shah22a,
title = { Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge },
author = {Shah, Abhin and Shanmugam, Karthikeyan and Ahuja, Kartik},
booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics},
pages = {5538--5562},
year = {2022},
editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel},
volume = {151},
series = {Proceedings of Machine Learning Research},
month = {28--30 Mar},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v151/shah22a/shah22a.pdf},
url = {https://proceedings.mlr.press/v151/shah22a.html},
abstract = { Treatment effect estimation from observational data is a fundamental problem in causal inference. There are two very different schools of thought that have tackled this problem. On the one hand, the Pearlian framework commonly assumes structural knowledge (provided by an expert) in the form of directed acyclic graphs and provides graphical criteria such as the back-door criterion to identify the valid adjustment sets. On the other hand, the potential outcomes (PO) framework commonly assumes that all the observed features satisfy ignorability (i.e., no hidden confounding), which in general is untestable. In prior works that attempted to bridge these frameworks, there is an observational criteria to identify an