Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects

Aaron Fisher
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13706-13733, 2024.

Abstract

Many methods for estimating conditional average treatment effects (CATEs) can be expressed as weighted pseudo-outcome regressions (PORs). Previous comparisons of POR techniques have paid careful attention to the choice of pseudo-outcome transformation. However, we argue that the dominant driver of performance is actually the choice of weights. For example, we point out that R-Learning implicitly performs a POR with inverse-variance weights (IVWs). In the CATE setting, IVWs mitigate the instability associated with inverse-propensity weights, and lead to convenient simplifications of bias terms. We demonstrate the superior performance of IVWs in simulations, and derive convergence rates for IVWs that are, to our knowledge, the fastest yet shown without assuming knowledge of the covariate distribution.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-fisher24a, title = {Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects}, author = {Fisher, Aaron}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {13706--13733}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/fisher24a/fisher24a.pdf}, url = {https://proceedings.mlr.press/v235/fisher24a.html}, abstract = {Many methods for estimating conditional average treatment effects (CATEs) can be expressed as weighted pseudo-outcome regressions (PORs). Previous comparisons of POR techniques have paid careful attention to the choice of pseudo-outcome transformation. However, we argue that the dominant driver of performance is actually the choice of weights. For example, we point out that R-Learning implicitly performs a POR with inverse-variance weights (IVWs). In the CATE setting, IVWs mitigate the instability associated with inverse-propensity weights, and lead to convenient simplifications of bias terms. We demonstrate the superior performance of IVWs in simulations, and derive convergence rates for IVWs that are, to our knowledge, the fastest yet shown without assuming knowledge of the covariate distribution.} }
Endnote
%0 Conference Paper %T Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects %A Aaron Fisher %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-fisher24a %I PMLR %P 13706--13733 %U https://proceedings.mlr.press/v235/fisher24a.html %V 235 %X Many methods for estimating conditional average treatment effects (CATEs) can be expressed as weighted pseudo-outcome regressions (PORs). Previous comparisons of POR techniques have paid careful attention to the choice of pseudo-outcome transformation. However, we argue that the dominant driver of performance is actually the choice of weights. For example, we point out that R-Learning implicitly performs a POR with inverse-variance weights (IVWs). In the CATE setting, IVWs mitigate the instability associated with inverse-propensity weights, and lead to convenient simplifications of bias terms. We demonstrate the superior performance of IVWs in simulations, and derive convergence rates for IVWs that are, to our knowledge, the fastest yet shown without assuming knowledge of the covariate distribution.
APA
Fisher, A.. (2024). Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:13706-13733 Available from https://proceedings.mlr.press/v235/fisher24a.html.

Related Material