Proximal Causal Inference for Synthetic Control with Surrogates

Jizhou Liu, Eric Tchetgen Tchetgen, Carlos Varjão
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:730-738, 2024.

Abstract

The synthetic control method (SCM) has become a popular tool for estimating causal effects in policy evaluation, where a single treated unit is observed. However, SCM faces challenges in accurately predicting post-intervention potential outcomes had, contrary to fact, the treatment been withheld, when the pre-intervention period is short or the post-intervention period is long. To address these issues, we propose a novel method that leverages post-intervention information, specifically time-varying correlates of the causal effect called "surrogates", within the synthetic control framework. We establish conditions for identifying model parameters using the proximal inference framework and apply the generalized method of moments (GMM) approach for estimation and inference about the average treatment effect on the treated (ATT). Interestingly, we uncover specific conditions under which exclusively using post-intervention data suffices for estimation within our framework. Through a synthetic experiment and a real-world application, we demonstrate that our method can outperform other synthetic control methods in estimating both short-term and long-term effects, yielding more accurate inferences.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-liu24a, title = {Proximal Causal Inference for Synthetic Control with Surrogates}, author = {Liu, Jizhou and Tchetgen Tchetgen, Eric and Varj\~{a}o, Carlos}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {730--738}, 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/liu24a/liu24a.pdf}, url = {https://proceedings.mlr.press/v238/liu24a.html}, abstract = {The synthetic control method (SCM) has become a popular tool for estimating causal effects in policy evaluation, where a single treated unit is observed. However, SCM faces challenges in accurately predicting post-intervention potential outcomes had, contrary to fact, the treatment been withheld, when the pre-intervention period is short or the post-intervention period is long. To address these issues, we propose a novel method that leverages post-intervention information, specifically time-varying correlates of the causal effect called "surrogates", within the synthetic control framework. We establish conditions for identifying model parameters using the proximal inference framework and apply the generalized method of moments (GMM) approach for estimation and inference about the average treatment effect on the treated (ATT). Interestingly, we uncover specific conditions under which exclusively using post-intervention data suffices for estimation within our framework. Through a synthetic experiment and a real-world application, we demonstrate that our method can outperform other synthetic control methods in estimating both short-term and long-term effects, yielding more accurate inferences.} }
Endnote
%0 Conference Paper %T Proximal Causal Inference for Synthetic Control with Surrogates %A Jizhou Liu %A Eric Tchetgen Tchetgen %A Carlos Varjão %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-liu24a %I PMLR %P 730--738 %U https://proceedings.mlr.press/v238/liu24a.html %V 238 %X The synthetic control method (SCM) has become a popular tool for estimating causal effects in policy evaluation, where a single treated unit is observed. However, SCM faces challenges in accurately predicting post-intervention potential outcomes had, contrary to fact, the treatment been withheld, when the pre-intervention period is short or the post-intervention period is long. To address these issues, we propose a novel method that leverages post-intervention information, specifically time-varying correlates of the causal effect called "surrogates", within the synthetic control framework. We establish conditions for identifying model parameters using the proximal inference framework and apply the generalized method of moments (GMM) approach for estimation and inference about the average treatment effect on the treated (ATT). Interestingly, we uncover specific conditions under which exclusively using post-intervention data suffices for estimation within our framework. Through a synthetic experiment and a real-world application, we demonstrate that our method can outperform other synthetic control methods in estimating both short-term and long-term effects, yielding more accurate inferences.
APA
Liu, J., Tchetgen Tchetgen, E. & Varjão, C.. (2024). Proximal Causal Inference for Synthetic Control with Surrogates. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:730-738 Available from https://proceedings.mlr.press/v238/liu24a.html.

Related Material