Sihui Zhao, Xinbo Wang, Lin Liu, Xin Zhang
arXiv 13 Nov 2024 · Statistics — Methodology · 1 citations (OpenAlex)
arXiv:2411.08491 · PDF · DOI · OpenAlex · Extracted main text
Higher-Order Influence Functions (HOIF), developed in a series of papers over the past twenty years, is a fundamental theoretical device for constructing rate-optimal causal-effect estimators from observational studies. However, the value of HOIF for analyzing well-conducted randomized controlled trials (RCTs) has not been explicitly explored. In the recent U.S. Food and Drug Administration (FDA) and European Medicines Agency (EMA) guidelines on the practice of covariate adjustment in analyzing RCTs, in addition to the simple, unadjusted difference-in-mean estimator, it was also recommended to report the estimator adjusting for baseline covariates via a simple parametric working model, such as a linear model. In this paper, we show that a HOIF-motivated estimator for the treatment-specific mean has significantly improved statistical properties compared to popular adjusted estimators in practice when the number of baseline covariates $p$ is relatively large compared to the sample size $n$. We also characterize the conditions under which the HOIF-motivated estimator improves upon the unadjusted one. Furthermore, we demonstrate that a novel debiased adjusted estimator proposed recently by Lu et al. is, in fact, another HOIF-motivated estimator in disguise. Numerical and empirical studies are conducted to corroborate our theoretical findings.
appendix boundary found by appendix_command · 33% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Wei Ma, Fuyi Tu, and Hanzhong Liu (2022) Regression analysis for covariate-adaptive randomization: A robust and efficient inference perspective | 1.000 | 5 | 3 | 100% |
| 2 | Ting Ye, Jun Shao, Yanyao Yi, and Qingyuan Zhao (2023) Toward better practice of covariate adjustment in analyzing randomized clinical trials | 1.000 | 5 | 3 | 100% |
| 3 | Xin Lu, Fan Yang, and Yuhao Wang (2025) Debiased regression adjustment in completely randomized experiments with moderately high-dimensional covariates | 0.969 | 11 | 3 | 91% |
| 4 | Lihua Lei and Peng Ding (2021) Regression adjustment in completely randomized experiments with a diverging number of covariates | 0.941 | 12 | 4 | 83% |
| 5 | Lin Liu, Rajarshi Mukherjee, and James M Robins (2020) On nearly assumption-free tests of nominal confidence interval coverage for causal parameters estimated by machine learning self | 0.874 | 7 | 2 | 100% |
| 6 | Liang Jiang, Liyao Li, Ke Miao, and Yichong Zhang (2025) Adjustments with many regressors under covariate-adaptive randomizations | 0.874 | 6 | 2 | 100% |
| 7 | Haoge Chang, Joel A Middleton, and Peter M Aronow (2024) Exact bias correction for linear adjustment of randomized controlled trials | 0.874 | 5 | 2 | 100% |
| 8 | Lin Liu and Chang Li (2023) New $n$-consistent, numerically stable empirical higher-order influence function estimators self | 0.874 | 5 | 2 | 100% |
| 9 | Rabi N Bhattacharya and Jayanta K Ghosh (1992) A class of $U$-statistics and asymptotic normality of the number of $k$-clusters | 0.644 | 4 | 1 | 100% |
| 10 | Winston Lin (2013) Agnostic notes on regression adjustments to experimental data: Reexamining Freedman's critique | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 43 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.
| Citing paper | Intensity | Mentions | Sections | |
|---|---|---|---|---|
| 1 | Assumption-lean covariate adjustment under covariate adaptive randomization when $p = o (n)$ | 0.874 | 5 | 2 |
| 2 | Unbiased Regression-Adjusted Estimation of Average Treatment Effects in Randomized Controlled Trials | 0.405 | 1 | 1 |