Interpretable Sensitivity Analysis for Balancing Weights

TL;DR

This paper introduces a new sensitivity analysis framework for balancing weights estimators in observational studies, enabling valid confidence intervals and interpretability regarding unmeasured confounding.

Contribution

It develops a bootstrap-based sensitivity analysis method with interpretability features for balancing weights estimators, extending causal inference tools.

Findings

Bootstrap procedure provides valid confidence intervals under unmeasured confounding.

Method offers interpretable sensitivity parameters for balancing weights.

Extensive real data examples demonstrate practical applicability.

Abstract

Assessing sensitivity to unmeasured confounding is an important step in observational studies, which typically estimate effects under the assumption that all confounders are measured. In this paper, we develop a sensitivity analysis framework for balancing weights estimators, an increasingly popular approach that solves an optimization problem to obtain weights that directly minimizes covariate imbalance. In particular, we adapt a sensitivity analysis framework using the percentile bootstrap for a broad class of balancing weights estimators. We prove that the percentile bootstrap procedure can, with only minor modifications, yield valid confidence intervals for causal effects under restrictions on the level of unmeasured confounding. We also propose an amplification to allow for interpretable sensitivity parameters in the balancing weights framework. We illustrate our method through extensive real data examples.