Many social events and policy interventions generate treatment effects that persistently spill over into neighboring areas, causing interference in both time and space. In this paper, we propose a design-based framework to identify and estimate these spillover effects in panel data, when temporal and spatial interference intertwine with each other in complex ways that are unknown to researchers. Our framework defines estimands that enable researchers to measure the influence of each type of interference, and we propose estimators that are consistent and asymptotically normal under the assumption of sequential ignorability and mild regularity conditions. We show that conventional methods in panel data analysis, such as the difference-in-differences (DID) estimator or fixed effects models, can lead to significant biases in such scenarios. We test the method's performance on both simulated datasets and the replication of an empirical study from political science.

翻译：许多社会事件和政策干预产生的处理效应会持续溢出至邻近区域，导致时间和空间上的相互干扰。本文提出一个基于设计框架的方法，在面板数据中识别并估计这些溢出效应，当时间干扰与空间干扰以研究者未知的复杂方式相互交织时。我们的框架定义了可估量参数，使研究者能够衡量每种干扰类型的影响，并提出了在序列可忽略性假设及温和正则条件下具有一致性和渐近正态性的估计量。我们证明，面板数据分析中的常规方法（如双重差分估计量或固定效应模型）在此类场景下可能产生显著偏差。通过模拟数据集及对政治学实证研究的复现，我们检验了该方法的表现。