A Framework for Optimal Matching for Causal Inference

Abstract

We propose a novel framework for matching estimators for causal effect from observational data that is based on minimizing the dual norm of estimation error when expressed as an operator. We show that many popular matching estimators can be expressed as optimal in this framework, including nearest-neighbor matching, coarsened exact matching, and mean-matched sampling. This reveals their motivation and aptness as structural priors formulated by embedding the effect in a particular functional space. This also gives rise to a range of new, kernel-based matching estimators that arise when one embeds the effect in a reproducing kernel Hilbert space. Depending on the case, these estimators can be found using either quadratic optimization or integer optimization. We show that estimators based on universal kernels are universally consistent without model specification. In empirical results using both synthetic and real data, the new, kernel-based estimators outperform all standard causal estimators in estimation error.

Cited by in corpus (6)

• Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects
• Generalized Optimal Matching Methods for Causal Inference
• DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training
• Doubly robust off-policy evaluation with shrinkage
• MALTS: Matching After Learning to Stretch
• A Balancing Weight Framework for Estimating the Causal Effect of General Treatments