Hidden yet quantifiable: A lower bound for confounding strength using randomized trials

Piersilvio De Bartolomeis, Javier Abad Martinez, Konstantin Donhauser, Fanny Yang
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:1045-1053, 2024.

Abstract

In the era of fast-paced precision medicine, observational studies play a major role in properly evaluating new treatments in clinical practice. Yet, unobserved confounding can significantly compromise causal conclusions drawn from non-randomized data. We propose a novel strategy that leverages randomized trials to quantify unobserved confounding. First, we design a statistical test to detect unobserved confounding above a certain strength. Then, we use the test to estimate an asymptotically valid lower bound on the unobserved confounding strength. We evaluate the power and validity of our statistical test on several synthetic and semi-synthetic datasets. Further, we show how our lower bound can correctly identify the absence and presence of unobserved confounding in a real-world example.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-de-bartolomeis24a, title = {Hidden yet quantifiable: A lower bound for confounding strength using randomized trials}, author = {De Bartolomeis, Piersilvio and Abad Martinez, Javier and Donhauser, Konstantin and Yang, Fanny}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {1045--1053}, 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/de-bartolomeis24a/de-bartolomeis24a.pdf}, url = {https://proceedings.mlr.press/v238/de-bartolomeis24a.html}, abstract = {In the era of fast-paced precision medicine, observational studies play a major role in properly evaluating new treatments in clinical practice. Yet, unobserved confounding can significantly compromise causal conclusions drawn from non-randomized data. We propose a novel strategy that leverages randomized trials to quantify unobserved confounding. First, we design a statistical test to detect unobserved confounding above a certain strength. Then, we use the test to estimate an asymptotically valid lower bound on the unobserved confounding strength. We evaluate the power and validity of our statistical test on several synthetic and semi-synthetic datasets. Further, we show how our lower bound can correctly identify the absence and presence of unobserved confounding in a real-world example.} }
Endnote
%0 Conference Paper %T Hidden yet quantifiable: A lower bound for confounding strength using randomized trials %A Piersilvio De Bartolomeis %A Javier Abad Martinez %A Konstantin Donhauser %A Fanny Yang %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-de-bartolomeis24a %I PMLR %P 1045--1053 %U https://proceedings.mlr.press/v238/de-bartolomeis24a.html %V 238 %X In the era of fast-paced precision medicine, observational studies play a major role in properly evaluating new treatments in clinical practice. Yet, unobserved confounding can significantly compromise causal conclusions drawn from non-randomized data. We propose a novel strategy that leverages randomized trials to quantify unobserved confounding. First, we design a statistical test to detect unobserved confounding above a certain strength. Then, we use the test to estimate an asymptotically valid lower bound on the unobserved confounding strength. We evaluate the power and validity of our statistical test on several synthetic and semi-synthetic datasets. Further, we show how our lower bound can correctly identify the absence and presence of unobserved confounding in a real-world example.
APA
De Bartolomeis, P., Abad Martinez, J., Donhauser, K. & Yang, F.. (2024). Hidden yet quantifiable: A lower bound for confounding strength using randomized trials. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:1045-1053 Available from https://proceedings.mlr.press/v238/de-bartolomeis24a.html.

Related Material