A General Method for Deriving Tight Symbolic Bounds on Causal Effects

DOI10.1080/10618600.2022.2071905arXiv2003.10702OpenAlexW4225275056MaRDI QIDQ6094085FDOQ6094085

Authors: Michael C. Sachs, A. Sjölander, Erin E. Gabriel 

Publication date: 9 October 2023

Published in: Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Abstract: A causal query will commonly not be identifiable from observed data, in which case no estimator of the query can be contrived without further assumptions or measured variables, regardless of the amount or precision of the measurements of observed variables. However, it may still be possible to derive symbolic bounds on the query in terms of the distribution of observed variables. Bounds, numeric or symbolic, can often be more valuable than a statistical estimator derived under implausible assumptions. Symbolic bounds, however, provide a measure of uncertainty and information loss due to the lack of an identifiable estimand even in the absence of data. We develop and describe a general approach for computation of symbolic bounds and characterize a class of settings in which our method is guaranteed to provide tight valid bounds. This expands the known settings in which tight causal bounds are solutions to linear programs. We also prove that our method can provide valid and possibly informative symbolic bounds that are not guaranteed to be tight in a larger class of problems. We illustrate the use and interpretation of our algorithms in three examples in which we derive novel symbolic bounds.

Full work available at URL: https://arxiv.org/abs/2003.10702

Recommendations

• Bounds on causal interactions for binary outcomes
• Estimating bounds on causal effects in high-dimensional and possibly confounded systems
• Nonparametric Bounds for Causal Effects in Imperfect Randomized Experiments
• Causal bounds and observable constraints for non-deterministic models
• Bounding a linear causal effect using relative correlation restrictions
• Bounds on average causal effects in studies with a latent response variable
• Simplifying probabilistic expressions in causal inference

zbMATH Keywords

causal inferenceunmeasured confoundingcausal bounds

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Title not available (Why is that?)
• Identification and Estimation of Local Average Treatment Effects
• Causality. Models, reasoning, and inference
• Mendelian randomization as an instrumental variable approach to causal inference
• Analytic bounds on causal risk differences in directed acyclic graphs involving three observed binary variables
• Bounds on Direct Effects in the Presence of Confounded Intermediate Variables
• Bounds on Treatment Effects From Studies With Imperfect Compliance
• Title not available (Why is that?)
• Nonparametric Bounds for Causal Effects in Imperfect Randomized Experiments
• Probabilities of causation: Bounds and identification
• Causal bounds and observable constraints for non-deterministic models
• Bounds on causal interactions for binary outcomes
• Causal Bounds for Outcome-Dependent Sampling in Observational Studies

Cited In (1)

• Efficient computation of counterfactual bounds

This page was built for publication: A General Method for Deriving Tight Symbolic Bounds on Causal Effects

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6094085)