A Sensitivity Approach to Causal Inference Under Limited Overlap

2025/11/27 by Yuanzhe Ma, Huang, Yian, Ma, Yuanzhe +2
Decision Sciences · Mathematics · #Advanced Causal Inference Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Meta-analysis and systematic reviews #Methodology (stat.ME) #Statistical Methods and Bayesian Inference

paper · pdf · doi:10.48550/arxiv.2511.22003

openalex publication_date 2025/11/27 · openalex created_date 2025/12/03 · openalex updated_date 2026/08/01

Abstract

Limited overlap between treated and control groups is a key challenge in observational analysis. Standard approaches like trimming importance weights can reduce variance but introduce a fundamental bias. We propose a sensitivity framework for contextualizing findings under limited overlap, where we assess how irregular the outcome function has to be in order for the main finding to be invalidated. Our approach is based on worst-case confidence bounds on the bias introduced by standard trimming practices, under explicit assumptions necessary to extrapolate counterfactual estimates from regions of overlap to those without. Empirically, we demonstrate how our sensitivity framework protects against spurious findings by quantifying uncertainty in regions with limited overlap.

Citations

• Doubly Robust Estimators with Weak Overlap
• Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions
• Falsification before Extrapolation in Causal Effect Estimation
• Robust Inference Using Inverse Probability Weighting
• Time-uniform, nonparametric, nonasymptotic confidence sequences
• Overlap in Observational Studies with High-Dimensional Covariates
• Estimation and Inference for Moments of Ratios with Robustness against Large Trimming Bias
• On Adaptive Propensity Score Truncation in Causal Inference
• Generalized Optimal Matching Methods for Causal Inference
• Bias-Corrected Matching Estimators for Average Treatment Effects
• Treatment Effects in the Presence of Unmeasured Confounding: Dealing With Observations in the Tails of the Propensity Score Distribution--A Simulation Study
• Dealing with limited overlap in estimation of average treatment effects
• Constructing Inverse Probability Weights for Marginal Structural Models
• Confidence Intervals for Partially Identified Parameters
• The central role of the propensity score in observational studies for causal effects

Related

• Robust Sensitivity Analysis via Augmented Percentile Bootstrap under Simultaneous Violations of Unconfoundedness and Overlap
• Overlap violations in external validity
• Asymptotic causal inference with observational studies trimmed by the estimated propensity scores
• A Sensitivity Analysis Framework for Causal Inference Under Interference
• Overlap in Observational Studies with High-Dimensional Covariates