Journal article
Journal of the American Statistical Association, 2021
APA
Click to copy
Yin, M., Shi, C., Wang, Y., & Blei, D. (2021). Conformal Sensitivity Analysis for Individual Treatment Effects. Journal of the American Statistical Association.
Chicago/Turabian
Click to copy
Yin, Mingzhang, Claudia Shi, Yixin Wang, and D. Blei. “Conformal Sensitivity Analysis for Individual Treatment Effects.” Journal of the American Statistical Association (2021).
MLA
Click to copy
Yin, Mingzhang, et al. “Conformal Sensitivity Analysis for Individual Treatment Effects.” Journal of the American Statistical Association, 2021.
BibTeX Click to copy
@article{mingzhang2021a,
title = {Conformal Sensitivity Analysis for Individual Treatment Effects},
year = {2021},
journal = {Journal of the American Statistical Association},
author = {Yin, Mingzhang and Shi, Claudia and Wang, Yixin and Blei, D.}
}
Estimating an individual treatment effect (ITE) is essential to personalized decision making. However, existing methods for estimating the ITE often rely on unconfoundedness, an assumption that is fundamentally untestable with observed data. To assess the robustness of individual-level causal conclusion with unconfoundedness, this paper proposes a method for sensitivity analysis of the ITE, a way to estimate a range of the ITE under unobserved confounding. The method we develop quantifies unmeasured confounding through a marginal sensitivity model [Ros2002, Tan2006], and adapts the framework of conformal inference to estimate an ITE interval at a given confounding strength. In particular, we formulate this sensitivity analysis problem as a conformal inference problem under distribution shift, and we extend existing methods of covariate-shifted conformal inference to this more general setting. The result is a predictive interval that has guaranteed nominal coverage of the ITE, a method that provides coverage with distribution-free and nonasymptotic guarantees. We evaluate the method on synthetic data and illustrate its application in an observational study.