Interpretable Almost-Exact Matching for Causal Inference

Awa Dieng, Yameng Liu, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:2445-2453, 2019.

Abstract

Matching methods are heavily used in the social and health sciences due to their interpretability. We aim to create the highest possible quality of treatment-control matches for categorical data in the potential outcomes framework. The method proposed in this work aims to match units on a weighted Hamming distance, taking into account the relative importance of the covariates; the algorithm aims to match units on as many relevant variables as possible. To do this, the algorithm creates a hierarchy of covariate combinations on which to match (similar to downward closure), in the process solving an optimization problem for each unit in order to construct the optimal matches. The algorithm uses a single dynamic program to solve all of the units’ optimization problems simultaneously. Notable advantages of our method over existing matching procedures are its high-quality interpretable matches, versatility in handling different data distributions that may have irrelevant variables, and ability to handle missing data by matching on as many available covariates as possible.

Cite this Paper

BibTeX
@InProceedings{pmlr-v89-dieng19b, title = {Interpretable Almost-Exact Matching for Causal Inference}, author = {Dieng, Awa and Liu, Yameng and Roy, Sudeepa and Rudin, Cynthia and Volfovsky, Alexander}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {2445--2453}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/dieng19b/dieng19b.pdf}, url = {https://proceedings.mlr.press/v89/dieng19b.html}, abstract = {Matching methods are heavily used in the social and health sciences due to their interpretability. We aim to create the highest possible quality of treatment-control matches for categorical data in the potential outcomes framework. The method proposed in this work aims to match units on a weighted Hamming distance, taking into account the relative importance of the covariates; the algorithm aims to match units on as many relevant variables as possible. To do this, the algorithm creates a hierarchy of covariate combinations on which to match (similar to downward closure), in the process solving an optimization problem for each unit in order to construct the optimal matches. The algorithm uses a single dynamic program to solve all of the units’ optimization problems simultaneously. Notable advantages of our method over existing matching procedures are its high-quality interpretable matches, versatility in handling different data distributions that may have irrelevant variables, and ability to handle missing data by matching on as many available covariates as possible.} }
Endnote
%0 Conference Paper %T Interpretable Almost-Exact Matching for Causal Inference %A Awa Dieng %A Yameng Liu %A Sudeepa Roy %A Cynthia Rudin %A Alexander Volfovsky %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-dieng19b %I PMLR %P 2445--2453 %U https://proceedings.mlr.press/v89/dieng19b.html %V 89 %X Matching methods are heavily used in the social and health sciences due to their interpretability. We aim to create the highest possible quality of treatment-control matches for categorical data in the potential outcomes framework. The method proposed in this work aims to match units on a weighted Hamming distance, taking into account the relative importance of the covariates; the algorithm aims to match units on as many relevant variables as possible. To do this, the algorithm creates a hierarchy of covariate combinations on which to match (similar to downward closure), in the process solving an optimization problem for each unit in order to construct the optimal matches. The algorithm uses a single dynamic program to solve all of the units’ optimization problems simultaneously. Notable advantages of our method over existing matching procedures are its high-quality interpretable matches, versatility in handling different data distributions that may have irrelevant variables, and ability to handle missing data by matching on as many available covariates as possible.
APA
Dieng, A., Liu, Y., Roy, S., Rudin, C. & Volfovsky, A.. (2019). Interpretable Almost-Exact Matching for Causal Inference. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:2445-2453 Available from https://proceedings.mlr.press/v89/dieng19b.html.

Related Material