偏斜数据在线实验中分块设计的优势
On the Benefit of Blocking for Online Experiments with Skewed Data
- Meta Platforms Inc（元平台公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文论证在线A/B测试中分块分配优于事后调整，虽精度提升有限（5-10%），但能避免偏差并局部化异常值，实现有效缩尾处理。
AI中文摘要：
本文主张在在线A/B测试中使用分块（分层）分配以处理高度偏斜的总体数据。尽管由于离散化的限制，分块仅带来适度的精度提升（5-10%），作者证明相较于事后统计调整，它提供了两个关键的结构性优势。首先，固定权重分块正确瞄准真实平均处理效应，避免了效率加权替代方案引入的严重偏差。其次，分块将极端异常值局部化，使得针对块内的缩尾处理能够有效控制噪声，同时不破坏尾端处理效应。
英文摘要：
This paper advocates for using blocked (stratified) assignment in online A/B tests to handle highly skewed population data. While blocking yields only modest precision gains (5-10%) due to the limits of discretization, the authors demonstrate it offers two crucial structural benefits over post-hoc statistical adjustments. First, fixed-weight blocking correctly targets the true average treatment effect, avoiding the severe bias introduced by efficiency-weighted alternatives. Second, blocking localizes extreme outliers, enabling targeted within-block winsorization that effectively controls noise without destroying the tail-end treatment effect.
