FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference

Abstract

A classical problem in causal inference is that of matching, where treatment units need to be matched to control units based on covariate information. In this work, we propose a method that computes high quality almost-exact matches for high-dimensional categorical datasets. This method, called FLAME (Fast Large-scale Almost Matching Exactly), learns a distance metric for matching using a hold-out training data set. In order to perform matching efficiently for large datasets, FLAME leverages techniques that are natural for query processing in the area of database management, and two implementations of FLAME are provided: the first uses SQL queries and the second uses bit-vector techniques. The algorithm starts by constructing matches of the highest quality (exact matches on all covariates), and successively eliminates variables in order to match exactly on as many variables as possible, while still maintaining interpretable high-quality matches and balance between treatment and control groups. We leverage these high quality matches to estimate conditional average treatment effects (CATEs). Our experiments show that FLAME scales to huge datasets with millions of observations where existing state-of-the-art methods fail, and that it achieves significantly better performance than other matching methods.

References in corpus (2)

• For objective causal inference, design trumps analysis
• MALTS: Matching After Learning to Stretch

Cited by in corpus (10)

• MALTS: Matching After Learning to Stretch
• Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference
• Causal inference from observational data: Estimating the effect of contributions on visitation frequency atLinkedIn
• dame-flame: A Python Library Providing Fast Interpretable Matching for Causal Inference
• A Minimax Surrogate Loss Approach to Conditional Difference Estimation
• Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation
• Interpretable Almost Matching Exactly for Causal Inference
• DeepRite: Deep Recurrent Inverse TreatmEnt Weighting for Adjusting Time-varying Confounding in Modern Longitudinal Observational Data
• Interpretable Almost-Matching-Exactly With Instrumental Variables
• A Framework for Inferring Causality from Multi-Relational Observational Data using Conditional Independence