Conditional Front-door Adjustment for Heterogeneous Treatment Assignment Effect Estimation Under Non-compliance

Winston Chen, Trenton Chang, Jenna Wiens
Proceedings of the sixth Conference on Health, Inference, and Learning, PMLR 287:194-230, 2025.

Abstract

Estimates of heterogeneous treatment assignment effects are valuable when making treatment decisions. Under the presence of non-compliance (e.g., patients do not adhere to their assigned treatment), the standard backdoor adjustment (SBD) and the conditional frond-door adjustment (CFD) can both recover unbiased estimates of the treatment assignment effects. Therefore, which is more suitable depends on their estimation variance. From existing literature, it is unclear which of the two produces lower-variance estimates. In this work, we demonstrate theoretically and empirically that CFD yields lower-variance estimates than SBD when the true effect of treatment assignment is small. Additionally, since CFD requires estimating multiple nuisance parameters, we introduce LobsterNet, a multi-task neural network that implements CFD with joint modeling. Empirically, LobsterNet reduces estimation error across several semi-synthetic and real-world datasets compared to baselines. Our findings suggest CFD with shared nuisance parameter modeling can improve treatment assignment effect estimation under non-compliance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v287-chen25a, title = {Conditional Front-door Adjustment for Heterogeneous Treatment Assignment Effect Estimation Under Non-compliance}, author = {Chen, Winston and Chang, Trenton and Wiens, Jenna}, booktitle = {Proceedings of the sixth Conference on Health, Inference, and Learning}, pages = {194--230}, year = {2025}, editor = {Xu, Xuhai Orson and Choi, Edward and Singhal, Pankhuri and Gerych, Walter and Tang, Shengpu and Agrawal, Monica and Subbaswamy, Adarsh and Sizikova, Elena and Dunn, Jessilyn and Daneshjou, Roxana and Sarker, Tasmie and McDermott, Matthew and Chen, Irene}, volume = {287}, series = {Proceedings of Machine Learning Research}, month = {25--27 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v287/main/assets/chen25a/chen25a.pdf}, url = {https://proceedings.mlr.press/v287/chen25a.html}, abstract = {Estimates of heterogeneous treatment assignment effects are valuable when making treatment decisions. Under the presence of non-compliance (e.g., patients do not adhere to their assigned treatment), the standard backdoor adjustment (SBD) and the conditional frond-door adjustment (CFD) can both recover unbiased estimates of the treatment assignment effects. Therefore, which is more suitable depends on their estimation variance. From existing literature, it is unclear which of the two produces lower-variance estimates. In this work, we demonstrate theoretically and empirically that CFD yields lower-variance estimates than SBD when the true effect of treatment assignment is small. Additionally, since CFD requires estimating multiple nuisance parameters, we introduce LobsterNet, a multi-task neural network that implements CFD with joint modeling. Empirically, LobsterNet reduces estimation error across several semi-synthetic and real-world datasets compared to baselines. Our findings suggest CFD with shared nuisance parameter modeling can improve treatment assignment effect estimation under non-compliance.} }
Endnote
%0 Conference Paper %T Conditional Front-door Adjustment for Heterogeneous Treatment Assignment Effect Estimation Under Non-compliance %A Winston Chen %A Trenton Chang %A Jenna Wiens %B Proceedings of the sixth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2025 %E Xuhai Orson Xu %E Edward Choi %E Pankhuri Singhal %E Walter Gerych %E Shengpu Tang %E Monica Agrawal %E Adarsh Subbaswamy %E Elena Sizikova %E Jessilyn Dunn %E Roxana Daneshjou %E Tasmie Sarker %E Matthew McDermott %E Irene Chen %F pmlr-v287-chen25a %I PMLR %P 194--230 %U https://proceedings.mlr.press/v287/chen25a.html %V 287 %X Estimates of heterogeneous treatment assignment effects are valuable when making treatment decisions. Under the presence of non-compliance (e.g., patients do not adhere to their assigned treatment), the standard backdoor adjustment (SBD) and the conditional frond-door adjustment (CFD) can both recover unbiased estimates of the treatment assignment effects. Therefore, which is more suitable depends on their estimation variance. From existing literature, it is unclear which of the two produces lower-variance estimates. In this work, we demonstrate theoretically and empirically that CFD yields lower-variance estimates than SBD when the true effect of treatment assignment is small. Additionally, since CFD requires estimating multiple nuisance parameters, we introduce LobsterNet, a multi-task neural network that implements CFD with joint modeling. Empirically, LobsterNet reduces estimation error across several semi-synthetic and real-world datasets compared to baselines. Our findings suggest CFD with shared nuisance parameter modeling can improve treatment assignment effect estimation under non-compliance.
APA
Chen, W., Chang, T. & Wiens, J.. (2025). Conditional Front-door Adjustment for Heterogeneous Treatment Assignment Effect Estimation Under Non-compliance. Proceedings of the sixth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 287:194-230 Available from https://proceedings.mlr.press/v287/chen25a.html.

Related Material