no code implementations • EMNLP (CINLP) 2021 • Graham Tierney, Alexander Volfovsky
We highlight the importance of using domain knowledge to perform dimension reduction on the text data, and describe a procedure to characterize indirect effects via text when the text is only observed in one arm of the experiment.
1 code implementation • 17 Dec 2023 • Srikar Katta, Harsh Parikh, Cynthia Rudin, Alexander Volfovsky
Many modern causal questions ask how treatments affect complex outcomes that are measured using wearable devices and sensors.
no code implementations • 23 Oct 2023 • Harsh Parikh, Quinn Lanners, Zade Akras, Sahar F. Zafar, M. Brandon Westover, Cynthia Rudin, Alexander Volfovsky
Our work operationalizes a safe and interpretable framework to identify optimal treatment regimes.
no code implementations • 4 Jul 2023 • Marco Morucci, Vittorio Orlandi, Harsh Parikh, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
Experimental and observational studies often lack validity due to untestable assumptions.
no code implementations • 3 Apr 2023 • Marco Morucci, Cynthia Rudin, Alexander Volfovsky
We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching, a longstanding tool in observational causal inference.
1 code implementation • 23 Feb 2023 • Quinn Lanners, Harsh Parikh, Alexander Volfovsky, Cynthia Rudin, David Page
Our goal is to produce methods for observational causal inference that are auditable, easy to troubleshoot, accurate for treatment effect estimation, and scalable to high-dimensional data.
no code implementations • 7 Dec 2022 • Alexandre Belloni, Fei Fang, Alexander Volfovsky
In contrast to previous work, the proposed procedure aims to approximate the relevant network interference patterns.
no code implementations • 9 Mar 2022 • Harsh Parikh, Kentaro Hoffman, Haoqi Sun, Wendong Ge, Jin Jing, Rajesh Amerineni, Lin Liu, Jimeng Sun, Sahar Zafar, Aaron Struck, Alexander Volfovsky, Cynthia Rudin, M. Brandon Westover
Having a maximum EA burden greater than 75% when untreated had a 22% increased chance of a poor outcome (severe disability or death), and mild but long-lasting EA increased the risk of a poor outcome by 14%.
1 code implementation • 15 Jun 2021 • Graham Tierney, Christopher Bail, Alexander Volfovsky
Analysis of short text, such as social media posts, is extremely difficult because of their inherent brevity.
1 code implementation • 6 Jan 2021 • Neha R. Gupta, Vittorio Orlandi, Chia-Rui Chang, Tianyu Wang, Marco Morucci, Pritam Dey, Thomas J. Howell, Xian Sun, Angikar Ghosal, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
dame-flame is a Python package for performing matching for observational causal inference on datasets containing discrete covariates.
1 code implementation • 3 Mar 2020 • Marco Morucci, Vittorio Orlandi, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
We propose a matching method for observational data that matches units with others in unit-specific, hyper-box-shaped regions of the covariate space.
no code implementations • 2 Mar 2020 • M. Usaid Awan, Marco Morucci, Vittorio Orlandi, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
We propose a matching method that recovers direct treatment effects from randomized experiments where units are connected in an observed network, and units that share edges can potentially influence each others' outcomes.
1 code implementation • 27 Jun 2019 • M. Usaid Awan, Yameng Liu, Marco Morucci, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
Uncertainty in the estimation of the causal effect in observational studies is often due to unmeasured confounding, i. e., the presence of unobserved covariates linking treatments and outcomes.
no code implementations • 18 Nov 2018 • Harsh Parikh, Cynthia Rudin, Alexander Volfovsky
In this work, we learn an interpretable distance metric for matching, which leads to substantially higher quality matches.
3 code implementations • 18 Jun 2018 • Yameng Liu, Aw Dieng, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
Notable advantages of our method over existing matching procedures are its high-quality 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.
no code implementations • 19 Jul 2017 • Tianyu Wang, Marco Morucci, M. Usaid Awan, Yameng Liu, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
In this work, we propose a method that computes high quality almost-exact matches for high-dimensional categorical datasets.
no code implementations • 25 Jun 2015 • Daniel L. Sussman, Alexander Volfovsky, Edoardo M. Airoldi
The recent explosion in the amount and dimensionality of data has exacerbated the need of trading off computational and statistical efficiency carefully, so that inference is both tractable and meaningful.