Sensitivity analysis via the proportion of unmeasured confounding

Abstract

In observational studies, identification of ATEs is generally achieved by assuming that the correct set of confounders has been measured and properly included in the relevant models. Because this assumption is both strong and untestable, a sensitivity analysis should be performed. Common approaches include modeling the bias directly or varying the propensity scores to probe the effects of a potential unmeasured confounder. In this paper, we take a novel approach whereby the sensitivity parameter is the "proportion of unmeasured confounding:" the proportion of units for whom the treatment is not as good as randomized even after conditioning on the observed covariates. We consider different assumptions on the probability of a unit being unconfounded. In each case, we derive sharp bounds on the average treatment effect as a function of the sensitivity parameter and propose nonparametric estimators that allow flexible covariate adjustment. We also introduce a one-number summary of a study's robustness to the number of confounded units. Finally, we explore finite-sample properties via simulation, and apply the methods to an observational database used to assess the effects of right heart catheterization.

arXiv comment41 pages, 5 figures

References in corpus (9)

• Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations
• Fast learning rates for plug-in classifiers
• Improving Point and Interval Estimates of Monotone Functions by Rearrangement
• Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy
• Minimax-optimal nonparametric regression in high dimensions
• Nonparametric Bounds and Sensitivity Analysis of Treatment Effects
• Additive Approximations in High Dimensional Nonparametric Regression via the SALSA
• Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrap
• Minimax-optimal rates for sparse additive models over kernel classes via convex programming

Cited by in corpus (6)

• Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination
• Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding
• Asymptotics of cut distributions and robust modular inference using Posterior Bootstrap
• Sensitivity Analysis for Unmeasured Confounding via Effect Extrapolation
• Robustness to missing data: breakdown point analysis
• Valid causal inference with unobserved confounding in high-dimensional settings