Abstract:Rerandomization enforces covariate balance across treatment groups in the design stage of experiments. Despite its intuitive appeal, its theoretical justification remains unsatisfying because its benefits of improving efficiency for estimating the average treatment effect diminish if we use regression adjustment in the analysis stage. To strengthen the theory of rerandomization, we show that it mitigates false discoveries resulting from $p$-hacking caused by strategically selecting covariates in regression adjustment to get more significant $p$-values. Moreover, we show that rerandomization with a sufficiently stringent threshold can resolve such $p$-hacking. As a byproduct, our theory offers guidance for choosing the threshold in rerandomization in practice.
From: Xin Lu [view email]
[v1]
Fri, 2 May 2025 09:25:51 UTC (64 KB)
[v2]
Sat, 8 Aug 2026 16:11:50 UTC (98 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。