Emulate randomized clinical trials using heterogeneous treatment effect estimation for personalized treatments: Methodology review and benchmark

Y Ling, P Upadhyaya, L Chen, X Jiang, Y Kim - Journal of biomedical …, 2023 - Elsevier
Big data and (deep) machine learning have been ambitious tools in digital medicine, but
these tools focus mainly on association. Intervention in medicine is about the causal effects …

The projected covariance measure for assumption-lean variable significance testing

AR Lundborg, I Kim, RD Shah… - The Annals of …, 2024 - projecteuclid.org
The projected covariance measure for assumption-lean variable significance testing Page 1
The Annals of Statistics 2024, Vol. 52, No. 6, 2851–2878 https://doi.org/10.1214/24-AOS2447 …

Rank-transformed subsampling: inference for multiple data splitting and exchangeable p-values

FR Guo, RD Shah - Journal of the Royal Statistical Society …, 2024 - academic.oup.com
Many testing problems are readily amenable to randomized tests, such as those employing
data splitting. However, despite their usefulness in principle, randomized tests have obvious …

A new central limit theorem for the augmented ipw estimator: Variance inflation, cross-fit covariance and beyond

K Jiang, R Mukherjee, S Sen, P Sur - arXiv preprint arXiv:2205.10198, 2022 - arxiv.org
Estimation of the average treatment effect (ATE) is a central problem in causal inference. In
recent times, inference for the ATE in the presence of high-dimensional covariates has been …

When is the estimated propensity score better? High-dimensional analysis and bias correction

F Su, W Mou, P Ding, MJ Wainwright - arXiv preprint arXiv:2303.17102, 2023 - arxiv.org
Anecdotally, using an estimated propensity score is superior to the true propensity score in
estimating the average treatment effect based on observational data. However, this claim …

Minimax semiparametric learning with approximate sparsity

J Bradic, V Chernozhukov, WK Newey… - arXiv preprint arXiv …, 2019 - arxiv.org
This paper is about the feasibility and means of root-n consistently estimating linear, mean-
square continuous functionals of a high dimensional, approximately sparse regression …

Efficient and robust semi-supervised estimation of ATE with partially annotated treatment and response

J Hou, R Mukherjee, T Cai - arXiv preprint arXiv:2110.12336, 2021 - arxiv.org
A notable challenge of leveraging Electronic Health Records (EHR) for treatment effect
assessment is the lack of precise information on important clinical variables, including the …

Model-assisted inference for covariate-specific treatment effects with high-dimensional data

P Wu, Z Tan, W Hu, XH Zhou - arXiv preprint arXiv:2105.11362, 2021 - arxiv.org
Covariate-specific treatment effects (CSTEs) represent heterogeneous treatment effects
across subpopulations defined by certain selected covariates. In this article, we consider …

A decorrelation method for general regression adjustment in randomized experiments

F Su, W Mou, P Ding, MJ Wainwright - arXiv preprint arXiv:2311.10076, 2023 - arxiv.org
We study regression adjustment with general function class approximations for estimating
the average treatment effect in the design-based setting. Standard regression adjustment …

Root-n consistent semiparametric learning with high-dimensional nuisance functions under minimal sparsity

L Liu, X Wang, Y Wang - arXiv preprint arXiv:2305.04174, 2023 - arxiv.org
Treatment effect estimation under unconfoundedness is a fundamental task in causal
inference. In response to the challenge of analyzing high-dimensional datasets collected in …