CLAM: Causal Spatial Disaggregation to Infer Local Effects From Coarse Data

2026-08-08

AI Summary

This study addresses the challenge of inferring fine-grained spatial causal effects from coarse-grained observational data in public policy contexts characterized by substantial local heterogeneity. The authors propose CLAM, a novel method that jointly models causal inference and spatial disaggregation for the first time, leveraging high-resolution contextual covariates to modulate local treatment effects. By simultaneously learning both the underlying causal mechanisms and the spatial disaggregation mapping, CLAM enables accurate estimation of localized causal effects, counterfactual reasoning, and outcome disaggregation. The approach effectively captures spatial interactions and heterogeneity typically overlooked by conventional methods that treat units independently. Empirical evaluations demonstrate that CLAM reliably recovers spatially varying causal effects across diverse real-world scenarios, offering a robust tool for fine-grained decision-making in domains such as public health and environmental policy.

Abstract

Learning fine-grained spatial patterns from coarse-resolution data is challenging, especially in causal settings where high-resolution effects must be inferred from aggregated interventions and outcomes. We introduce CLAM, a method for estimating localized causal effects from coarse observations by exploiting high-resolution contextual covariates that modulate these effects. By jointly learning the causal mechanism and a disaggregation mapping, CLAM captures interactions that are missed when addressing these problems independently. The method supports localized effect estimation, counterfactual reasoning, and principled outcome disaggregation, and reliably captures spatially varying causal effects across diverse settings. This is particularly relevant for applications such as public health and environmental policy, where decisions are made at broad scales despite substantial local heterogeneity. Code is available at https://github.com/gerritgr/clam

Problem

• causal inference
• spatial disaggregation
• local effects
• coarse data
• spatial heterogeneity

Innovation

• causal inference
• spatial disaggregation
• high-resolution covariates
• localized effects
• counterfactual reasoning