Algorithm Overview
Read the summaries below to determine which of our matching algorithms is right for you.
Dynamic Almost Matching Exactly (DAME)
Fast Large-Scale Almost Matching Exactly (FLAME)
Languages: | R, Python |
Input data: | Categorical covariates, scales well to large datasets with millions of observations |
Matching method: | Uses bit-vector computations to match units based on a learned, weighted Hamming distance. FLAME successively drops irrelevant covariates to lessen the computational load while still maintaining enough covariates for high-quality conditional average treatment effect (CATE) estimation. |
Paper: | FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference |
Matching After Learning to Stretch (MALTS)
Languages: | Python |
Input data: | Continuous, categorical, or mixed (continuous and categorical) covariates |
Matching method: | Uses exact matching for discrete variables and learned, generalized Mahalanobis distances for continuous variables. Instead of a predetermined distance metric, the covariates contributing more towards predicting the outcome are given higher weights. |
Paper: | MALTS: Matching After Learning to Stretch |
Adaptive Hyper-Box Matching (AHB)
Model-to-Match: Lasso Coefficient Matching (LCM)