Partial Identification

Follow this topic Ask about this topic

Partial identification asks which values of a causal effect, policy value, or other target remain compatible with observed data when point identification fails. Researchers derive sharp bounds or identified sets using linear programming, monotonicity and sensitivity assumptions, instrumental variables, missing-data models, and causal graphs, then build estimators and confidence intervals for those sets. Applications include treatment effects under hidden confounding, selective labels and missing outcomes, counterfactual harms, off-policy evaluation, and limits of machine-learning capability or preference measurements. Current work seeks tighter bounds and useful decisions or experiments without relying on implausible assumptions, while confronting a central limit: more observations can reduce sampling error but cannot resolve ambiguity built into the data or assumptions.

Latest papers

31 papers7 papers in the last four weeks, up 17% on the four weeks before. 0.0% of all new papers.

Uncertainty-aware Causal Decision Making via Effect Bound Decomposition
Jan 30, 2026Md Musfiqur Rahman, Ziwei Jiang, Hilaf Hasson +1Causal Effect Estimation Parameter Identifiability
Electrical and Computer Engineering, Purdue University · Computer Science, Johns Hopkins University · Cohesity

Jan 30, 2026J/K move · Enter open · S save

Uncertainty-aware Causal Decision Making via Effect Bound Decomposition

Md Musfiqur Rahman, Ziwei Jiang, Hilaf Hasson, Murat Kocaoglu

Electrical and Computer Engineering, Purdue University · Computer Science, Johns Hopkins University · Cohesity

Causal Effect Estimation Parameter Identifiability Partial Identification Causal Identifiability Decision-Making under Uncertainty Causal Inference with Unobserved Confounding

Open paper AskPDF arXiv

Causal inference from observational data can provide strong evidence for finding the best action in a decision-making scenario without having to perform expensive randomized trials. The causal effect of an action is often not pointwise identifiable even with infinite data due to unobserved confounding factors. Furthermore, having only finitely many samples adds another layer of uncertainty to causal effect estimation. Several existing methods can be used to obtain upper and lower bounds to the causal effect, ranging from symbolic methods to the more recent neural network-based approaches, which implicitly incorporate both sources of uncertainty. However, these methods do not inform whether collecting more samples may or may not help identify the best action from observational data, leaving experts in the dark about their data collection strategies. We address this problem with a novel framework that can distinguish the range of causal effect values that might be eliminated by collecting more samples from the range of values that, with high probability, cannot be eliminated with more observational samples. We show that this partitioning can be obtained by solving max-min and min-max optimization problems. We leverage neural causal models to approximately recover this decomposition in practice. We demonstrate via experiments on synthetic and real-world datasets that our algorithm can determine when collecting more samples will not help determine the best action. Our framework can help practitioners decide when to resort to non-observational studies or seek to measure some of the unmeasured confounders for optimal decision-making.