Optimal Experiments for Partial Causal Effect Identification

TL;DR

This paper develops a method to select the most cost-effective experiments that maximize the reduction of uncertainty in causal effect estimates, using graphical pruning and polynomial programming techniques.

Contribution

It introduces a novel framework for optimal experiment selection in causal inference, including pruning criteria and a demonstration on real observational data.

Findings

Pruning criteria reduce candidate experiments by 50-88% on benchmark networks.

ID-based pruning significantly decreases the search space for experiment subsets.

End-to-end application successfully identifies optimal experiments for causal effect estimation.

Abstract

Causal queries are often only partially identifiable from observational data, and experiments that could tighten the resulting bounds are typically costly. We study the problem of selecting, prior to observing experimental outcomes, a cost-constrained subset of experiments that maximally tightens bounds on a target query. We formalize this as the max-potency problem, where epistemic potency measures the worst-case reduction in bound width guaranteed by an experiment, and show that this problem is NP-hard via a reduction from 0-1 knapsack. Building on the polynomial-programming framework of Duarte et al. (2023), we give a general procedure for evaluating epistemic potency in discrete settings. To control the super-exponential search space, we introduce two graphical pruning criteria that depend only on the causal graph and the query: a novel path-interception rule that exploits district structure to certify zero potency in linear time, and an identifiability check based on the ID algorithm. On Erdos-Renyi random graphs and 11 bnlearn benchmark networks, the two criteria together prune 50-88% of candidate experiments on average without solving a single polynomial program. For the general subset search, we show that ID-pruned experiments are combinatorially inert, yielding a super-exponential reduction in the number of subsets evaluated. We close with an end-to-end demonstration on observational NHANES data, selecting optimal experiments for estimating the effect of physical activity on diabetes.