This paper addresses a classical problem in causal inference: matching, where treatment units need to be matched to control units. Some of the main challenges in developing matching methods arise from the tension among (i) inclusion of as many covariates as possible in defining the matched groups, (ii) having matched groups with enough treated and control units for a valid estimate of Average Treatment Effect (ATE) in each group, and (iii) computing the matched pairs efficiently for large datasets. Roy et al. propose a fast and novel method for approximate and exact matching in causal analysis called FLAME (Fast Large-scale Almost Matching Exactly). They define an optimization objective for match quality, which gives preferences to matching on covariates that can be useful for predicting the outcome while encouraging as many matches as possible. FLAME aims to optimize the match quality measure, leveraging techniques that are natural for query processing in the area of database management. The authors provide two implementations of FLAME using SQL queries and bit-vector techniques.
Read the paper:
FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference. S. Roy; C. Rudin; A. Volfovsky; T. Wang.