Extended sensitivity analysis for heterogeneous unmeasured confounding with an application to sibling studies of returns to education

DOI10.1214/18-AOAS1215zbMATH Open1423.62040arXiv1711.05570MaRDI QIDQ2318655FDOQ2318655

Colin B. Fogarty, Raiden B. Hasegawa

Publication date: 15 August 2019

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: The conventional model for assessing insensitivity to hidden bias in paired observational studies constructs a worst-case distribution for treatment assignments subject to bounds on the maximal bias to which any given pair is subjected. In studies where rare cases of extreme hidden bias are suspected, the maximal bias may be substantially larger than the typical bias across pairs, such that a correctly specified bound on the maximal bias would yield an unduly pessimistic perception of the study's robustness to hidden bias. We present an extended sensitivity analysis which allows researchers to simultaneously bound the maximal and typical bias perturbing the pairs under investigation while maintaining the desired Type I error rate. We motivate and illustrate our method with two sibling studies on the impact of schooling on earnings, one containing information of cognitive ability of siblings and the other not. Cognitive ability, clearly influential of both earnings and degree of schooling, is likely similar between members of most sibling pairs yet could, conceivably, vary drastically for some siblings. The method is straightforward to implement, simply requiring the solution to a quadratic program.

Full work available at URL: https://arxiv.org/abs/1711.05570

Recommendations

• Making sense of sensitivity: extending omitted variable bias
• Studentized sensitivity analysis for the sample average treatment effect in paired observational studies
• Sensitivity analysis of the unconfoundedness assumption with an application to an evaluation of college choice effects on earnings
• On sensitivity value of pair-matched observational studies
• Sensitivity analysis for two control groups

zbMATH Keywords

causal inferencequadratic programmingnuisance parametersobservational studieshidden biassuperpopulation inference

Mathematics Subject Classification ID

Applications of statistics to economics (62P20) Quadratic programming (90C20) Statistics of extreme values; tail inference (62G32) Applications of statistics to social sciences (62P25)

Cites Work

• Design of observational studies
• P Values Maximized Over a Confidence Set for the Nuisance Parameter
• Observational studies.
• Matching methods for causal inference: a review and a look forward
• Covariance adjustment in radomized experiments and observational studies
• On Estimation of the Survivor Average Causal Effect in Observational Studies When Important Confounders Are Missing Due to Death
• Sensitivity analysis for trend tests: application to the risk of radiation exposure
• The sensitivity of linear regression coefficients' confidence limits to the omission of a confounder
• Choice as an alternative to control in observational studies. (With comments and a rejoinder).
• Amplification of Sensitivity Analysis in Matched Observational Studies
• A Better Bound on the Variance
• Calibrating Sensitivity Analyses to Observed Covariates in Observational Studies
• Sensitivity analysis for certain permutation inferences in matched observational studies
• Detecting bias with confidence in observational studies
• Extended sensitivity analysis for heterogeneous unmeasured confounding with an application to sibling studies of returns to education
• Sensitivity analysis for matched pair analysis of binary data: From worst case to average case analysis

Cited In (5)

• Studentized Sensitivity Analysis for the Sample Average Treatment Effect in Paired Observational Studies
• Assessment of the extent of corroboration of an elaborate theory of a causal hypothesis using partial conjunctions of evidence factors
• Extended sensitivity analysis for heterogeneous unmeasured confounding with an application to sibling studies of returns to education
• Evidence factors from multiple, possibly invalid, instrumental variables
• Sharpening the Rosenbaum Sensitivity Bounds to Address Concerns About Interactions Between Observed and Unobserved Covariates

Uses Software

• R
• DOS

This page was built for publication: Extended sensitivity analysis for heterogeneous unmeasured confounding with an application to sibling studies of returns to education

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2318655)