Covariate-Adaptive Randomization in Network Data

Oregon Convention Center 

Users linked together through a network often tend to have similar behaviors. This phenomenon is usually known as network interaction. Users' covariates are often correlated with their outcomes. Therefore, one should incorporate both the covariates and the network information in a carefully designed randomization to improve the estimation of the average treatment effect (ATE) in network hypothesis testing. We propose a new adaptive procedure to balance both the network and the covariates. We show that the imbalance measures with respect to the covariates and the network are Op(1). We also demonstrate the relationships between the improved balances and the increased efficiency in terms of the mean square error (MSE). Numerical studies demonstrate the advanced performance of the proposed procedure regarding the greater comparability of the treatment groups and the reduction of MSE for estimating the ATE.

Adaptive design

Covariate balance

Network balance

Treatment effect estimation

Martingale 

Section on Statistical Learning and Data Science