Sensitivity Analysis via the Proportion of Unmeasured Confounding
From MaRDI portal
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.
Recommendations
- Assessing the Sensitivity of Regression Results to Unmeasured Confounders in Observational Studies
- On sensitivity value of pair-matched observational studies
- Sensitivity Analysis for Unmeasured Confounding in Meta-Analyses
- Sensitivity analysis for causal inference using inverse probability weighting
- Design sensitivity and efficiency in observational studies
Cites work
- Analysis of the binary instrumental variable model
- Assessing the Sensitivity of Regression Results to Unmeasured Confounders in Observational Studies
- Confidence Intervals for Partially Identified Parameters
- Covariance adjustment in radomized experiments and observational studies
- Differential effects and generic biases in observational studies
- Dual and simultaneous sensitivity analysis for matched pairs
- Fast learning rates for plug-in classifiers
- scientific article; zbMATH DE number 490141 (Why is no real title available?)
- Identification and Robustness with Contaminated and Corrupted Data
- Improving point and interval estimators of monotone functions by rearrangement
- Making sense of sensitivity: extending omitted variable bias
- Methods for conducting sensitivity analysis of trials with potentially nonignorable competing causes of censoring
- Minimax-optimal nonparametric regression in high dimensions
- Minimax-optimal rates for sparse additive models over kernel classes via convex programming
- Nonparametric bounds and sensitivity analysis of treatment effects
- Nonparametric causal effects based on incremental propensity score interventions
- Robust inference on average treatment effects with possibly more covariates than observations
- Semiparametric and nonparametric methods in econometrics
- Semiparametric theory and missing data.
- Sensitivity analysis for certain permutation inferences in matched observational studies
- Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrap
- Sharp instruments for classifying compliers and generalizing causal effects
- Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy
- Super Learner
- Survivor-complier effects in the presence of selection on treatment, with application to a study of prompt ICU admission
- Unified methods for censored longitudinal data and causality
- Weak convergence and empirical processes. With applications to statistics
Cited in
(25)- Sensitivity Analysis for Unmeasured Confounding in Meta-Analyses
- A flexible sensitivity analysis approach for unmeasured confounding with multiple treatments and a binary outcome with application to SEER-medicare lung cancer data
- Sensitivity of the bounds on the ATE in the presence of sample selection
- Alternative sensitivity analyses for regression estimates of treatment effects to unobserved confounding in binary and survival data
- Bounds on the conditional and average treatment effect with unobserved confounding factors
- Evaluating costs with unmeasured confounding: a sensitivity analysis for the treatment effect
- Sensitivity analysis for an unobserved moderator in RCT-to-target-population generalization of treatment effects
- Simplified Bayesian sensitivity analysis for mismeasured and unobserved confounders
- Sensitivity analysis for causal inference using inverse probability weighting
- Assessing the Sensitivity of Regression Results to Unmeasured Confounders in Observational Studies
- Making sense of sensitivity: extending omitted variable bias
- Sensitivity analysis of the unconfoundedness assumption with an application to an evaluation of college choice effects on earnings
- Flexible sensitivity analysis for observational studies without observable implications
- Balancing weights for region-level analysis: the effect of medicaid expansion on the uninsurance rate among states that did not expand medicaid
- Can we reliably detect biases that matter in observational studies?
- Bahadur Efficiency of Observational Block Designs
- Protocols for observational studies: methods and open problems
- Robustness to missing data: breakdown point analysis
- Efficient generalization and transportation
- Selecting subpopulations for causal inference in regression discontinuity designs
- Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confounding
- Semiparametric sensitivity analysis: unmeasured confounding in observational studies
- Reinforcement Learning with Continuous Actions Under Unmeasured Confounding
- Calibrated sensitivity models
- An average-case sensitivity analysis for unmeasured confounding
This page was built for publication: Sensitivity Analysis via the Proportion of Unmeasured Confounding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5881155)
