The Missing Corner: When Sharp Causal Bounds Fail to Compose
Abstract
Sharp bounds on two potential-outcome means need not combine into sharp bounds on their difference. We characterize exactly when composition is guaranteed across environments sharing a joint potential-outcome law. For binary treatment and outcome, fix strict selection-probability bounds and interior treatment propensities. Subtracting the full model's sharp mean intervals gives sharp average-treatment-effect bounds for every compatible observed law if and only if the absolute selection bounds coincide across environments. Under this alignment, the complete mean region is rectangular; its endpoints and attaining causal models require O(K) arithmetic operations for K environments. For every mismatch, failure occurs on a relatively open set of positive observed tables at the prescribed propensities and persists under small joint drift. We give computable perturbation certificates and an exact family whose gap is first order in the mismatch. A separate finite-confounding family shows when the lost joint information changes an identified causal sign. These results distinguish local marginal sharpness from joint attainability after combining environments.
Related
- Sharp Causal Bounds for Dynamic Treatment Regimes
- Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
- Identification and Estimation of Causal Estimands with Missing Not at Random Data
- Sharp Probabilistic Normwise Backward Error Bounds for LU Factorization
- Credible Bounds for Causal Quantities with Continuous Outcomes
BibTeX
@misc{qi2026missing,
title = {{The Missing Corner: When Sharp Causal Bounds Fail to Compose}},
author = {Yicheng Qi and Xiyi Xiong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.08197},
eprint = {2610.08197},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.08197},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - The Missing Corner: When Sharp Causal Bounds Fail to Compose
AU - Yicheng Qi
AU - Xiyi Xiong
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.08197
UR - https://arxiv.org/abs/2610.08197
AB - Sharp bounds on two potential-outcome means need not combine into sharp bounds on their difference. We characterize exactly when composition is guaranteed across environments sharing a joint potential-outcome law. For binary treatment and outcome, fix strict selection-probability bounds and interior treatment propensities. Subtracting the full model's sharp mean intervals gives sharp average-treatment-effect bounds for every compatible observed law if and only if the absolute selection bounds coincide across environments. Under this alignment, the complete mean region is rectangular; its endpoints and attaining causal models require O(K) arithmetic operations for K environments. For every mismatch, failure occurs on a relatively open set of positive observed tables at the prescribed propensities and persists under small joint drift. We give computable perturbation certificates and an exact family whose gap is first order in the mismatch. A separate finite-confounding family shows when the lost joint information changes an identified causal sign. These results distinguish local marginal sharpness from joint attainability after combining environments.
ER -