Bounding causal effects with leaky instruments

David Watson, Jordan Penn, Lee Gunderson, Gecia Bravo-Hermsdorff, Afsaneh Mastouri, Ricardo Silva
Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, PMLR 244:3689-3710, 2024.

Abstract

Instrumental variables (IVs) are a popular and powerful tool for estimating causal effects in the presence of unobserved confounding. However, classical approaches rely on strong assumptions such as the exclusion criterion, which states that instrumental effects must be entirely mediated by treatments. This assumption often fails in practice. When IV methods are improperly applied to data that do not meet the exclusion criterion, estimated causal effects may be badly biased. In this work, we propose a novel solution that provides partial identification in linear systems given a set of leaky instruments, which are allowed to violate the exclusion criterion to some limited degree. We derive a convex optimization objective that provides provably sharp bounds on the average treatment effect under some common forms of information leakage, and implement inference procedures to quantify the uncertainty of resulting estimates. We demonstrate our method in a set of experiments with simulated data, where it performs favorably against the state of the art. An accompanying $\texttt{R}$ package, $\texttt{leakyIV}$, is available from $\texttt{CRAN}$.

Cite this Paper

BibTeX
@InProceedings{pmlr-v244-watson24a, title = {Bounding causal effects with leaky instruments}, author = {Watson, David and Penn, Jordan and Gunderson, Lee and Bravo-Hermsdorff, Gecia and Mastouri, Afsaneh and Silva, Ricardo}, booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence}, pages = {3689--3710}, year = {2024}, editor = {Kiyavash, Negar and Mooij, Joris M.}, volume = {244}, series = {Proceedings of Machine Learning Research}, month = {15--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/watson24a/watson24a.pdf}, url = {https://proceedings.mlr.press/v244/watson24a.html}, abstract = {Instrumental variables (IVs) are a popular and powerful tool for estimating causal effects in the presence of unobserved confounding. However, classical approaches rely on strong assumptions such as the exclusion criterion, which states that instrumental effects must be entirely mediated by treatments. This assumption often fails in practice. When IV methods are improperly applied to data that do not meet the exclusion criterion, estimated causal effects may be badly biased. In this work, we propose a novel solution that provides partial identification in linear systems given a set of leaky instruments, which are allowed to violate the exclusion criterion to some limited degree. We derive a convex optimization objective that provides provably sharp bounds on the average treatment effect under some common forms of information leakage, and implement inference procedures to quantify the uncertainty of resulting estimates. We demonstrate our method in a set of experiments with simulated data, where it performs favorably against the state of the art. An accompanying $\texttt{R}$ package, $\texttt{leakyIV}$, is available from $\texttt{CRAN}$.} }
Endnote
%0 Conference Paper %T Bounding causal effects with leaky instruments %A David Watson %A Jordan Penn %A Lee Gunderson %A Gecia Bravo-Hermsdorff %A Afsaneh Mastouri %A Ricardo Silva %B Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2024 %E Negar Kiyavash %E Joris M. Mooij %F pmlr-v244-watson24a %I PMLR %P 3689--3710 %U https://proceedings.mlr.press/v244/watson24a.html %V 244 %X Instrumental variables (IVs) are a popular and powerful tool for estimating causal effects in the presence of unobserved confounding. However, classical approaches rely on strong assumptions such as the exclusion criterion, which states that instrumental effects must be entirely mediated by treatments. This assumption often fails in practice. When IV methods are improperly applied to data that do not meet the exclusion criterion, estimated causal effects may be badly biased. In this work, we propose a novel solution that provides partial identification in linear systems given a set of leaky instruments, which are allowed to violate the exclusion criterion to some limited degree. We derive a convex optimization objective that provides provably sharp bounds on the average treatment effect under some common forms of information leakage, and implement inference procedures to quantify the uncertainty of resulting estimates. We demonstrate our method in a set of experiments with simulated data, where it performs favorably against the state of the art. An accompanying $\texttt{R}$ package, $\texttt{leakyIV}$, is available from $\texttt{CRAN}$.
APA
Watson, D., Penn, J., Gunderson, L., Bravo-Hermsdorff, G., Mastouri, A. & Silva, R.. (2024). Bounding causal effects with leaky instruments. Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 244:3689-3710 Available from https://proceedings.mlr.press/v244/watson24a.html.

Related Material