EnsembleIV: Creating Instrumental Variables from Ensemble Learners for Robust Statistical Inference

no code implementations • 6 Mar 2023 • Gordon Burtch, Edward McFowland III, Mochen Yang, Gediminas Adomavicius

Despite increasing popularity in empirical studies, the integration of machine learning generated variables into regression models for statistical inference suffers from the measurement error problem, which can bias estimation and threaten the validity of inferences.

regression valid

Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspective

no code implementations • 17 Feb 2023 • Yash Travadi, Le Peng, Xuan Bi, Ju Sun, Mochen Yang

However, the economic considerations of the clients, such as fairness and incentive, are yet to be fully explored.

Distributed Computing Fairness +2

Achieving Reliable Causal Inference with Data-Mined Variables: A Random Forest Approach to the Measurement Error Problem

no code implementations • 19 Dec 2020 • Mochen Yang, Edward McFowland III, Gordon Burtch, Gediminas Adomavicius

The random forest algorithm performs best when comprised of a set of trees that are individually accurate in their predictions, yet which also make 'different' mistakes, i. e., have weakly correlated prediction errors.

BIG-bench Machine Learning Causal Inference +1