Confounding Feature Acquisition for Causal Effect Estimation

Shirly Wang, Seung Eun Yi, Shalmali Joshi, Marzyeh Ghassemi
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 136:379-396, 2020.

Abstract

Reliable treatment effect estimation from observational data depends on the availability of all confounding information. While much work has targeted treatment effect estimation from observational data, there is relatively little work in the setting of confounding variable missingness, where collecting more information on confounders is often costly or time-consuming. In this work, we frame this challenge as a problem of feature acquisition of confounding features for causal inference. Our goal is to prioritize acquiring values for a fixed and known subset of missing confounders in samples that lead to efficient average treatment effect estimation. We propose two acquisition strategies based on i) covariate balancing (CB), and ii) reducing statistical estimation error on observed factual outcome error (OE). We compare CB and OE on five common causal effect estimation methods, and demonstrate improved sample efficiency of OE over baseline methods under various settings. We also provide visualizations for further analysis on the difference between our proposed methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v136-wang20a, title = {Confounding Feature Acquisition for Causal Effect Estimation}, author = {Wang, Shirly and Yi, Seung Eun and Joshi, Shalmali and Ghassemi, Marzyeh}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {379--396}, year = {2020}, editor = {Alsentzer, Emily and McDermott, Matthew B. A. and Falck, Fabian and Sarkar, Suproteem K. and Roy, Subhrajit and Hyland, Stephanie L.}, volume = {136}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v136/wang20a/wang20a.pdf}, url = {https://proceedings.mlr.press/v136/wang20a.html}, abstract = {Reliable treatment effect estimation from observational data depends on the availability of all confounding information. While much work has targeted treatment effect estimation from observational data, there is relatively little work in the setting of confounding variable missingness, where collecting more information on confounders is often costly or time-consuming. In this work, we frame this challenge as a problem of feature acquisition of confounding features for causal inference. Our goal is to prioritize acquiring values for a fixed and known subset of missing confounders in samples that lead to efficient average treatment effect estimation. We propose two acquisition strategies based on i) covariate balancing (CB), and ii) reducing statistical estimation error on observed factual outcome error (OE). We compare CB and OE on five common causal effect estimation methods, and demonstrate improved sample efficiency of OE over baseline methods under various settings. We also provide visualizations for further analysis on the difference between our proposed methods.} }
Endnote
%0 Conference Paper %T Confounding Feature Acquisition for Causal Effect Estimation %A Shirly Wang %A Seung Eun Yi %A Shalmali Joshi %A Marzyeh Ghassemi %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Emily Alsentzer %E Matthew B. A. McDermott %E Fabian Falck %E Suproteem K. Sarkar %E Subhrajit Roy %E Stephanie L. Hyland %F pmlr-v136-wang20a %I PMLR %P 379--396 %U https://proceedings.mlr.press/v136/wang20a.html %V 136 %X Reliable treatment effect estimation from observational data depends on the availability of all confounding information. While much work has targeted treatment effect estimation from observational data, there is relatively little work in the setting of confounding variable missingness, where collecting more information on confounders is often costly or time-consuming. In this work, we frame this challenge as a problem of feature acquisition of confounding features for causal inference. Our goal is to prioritize acquiring values for a fixed and known subset of missing confounders in samples that lead to efficient average treatment effect estimation. We propose two acquisition strategies based on i) covariate balancing (CB), and ii) reducing statistical estimation error on observed factual outcome error (OE). We compare CB and OE on five common causal effect estimation methods, and demonstrate improved sample efficiency of OE over baseline methods under various settings. We also provide visualizations for further analysis on the difference between our proposed methods.
APA
Wang, S., Yi, S.E., Joshi, S. & Ghassemi, M.. (2020). Confounding Feature Acquisition for Causal Effect Estimation. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 136:379-396 Available from https://proceedings.mlr.press/v136/wang20a.html.

Related Material