Randomized graph cluster randomization
Randomized graph cluster randomization
复制标题
随机图簇随机化
作者：
J. Ugander;Hao Yin
摘要全局平均处理效应(GATE)是网络干扰下因果推理研究中的一个重要问题。有了正确指定的干扰曝光模型，门的Horvitz-Thompson(HT)和Hájek估计器分别是无偏和一致的，但已知在许多设计和许多感兴趣的环境下表现出极大的方差。通过干扰图的固定聚类，图簇随机化(GCR)设计已被证明与节点级随机分配相比极大地减小了方差，但即使如此，方差通常仍然大得令人望而却步。在这项工作中，我们提出了一种GCR设计的随机化版本，描述性地称为随机化图簇随机化(RGCR)，它使用随机聚类而不是单一固定聚类。通过考虑许多不同的分簇分配的集成，该设计避免了GCR的一个关键问题，即在单个分簇中，给定节点的网络暴露概率可能指数地小。我们提出了两种用于RGCR设计的内在随机化的图分解算法，随机化的3-网和1-跳-最大，改编自以前关于多向图切割问题和(图)度量的概率近似的工作。我们还提出了这两种算法的加权扩展，具有轻微的附加优势。所有这些算法都会产生可以有效估计的网络暴露概率。我们根据驱动干扰的图的度量结构，推导出门的HT估计器的方差的结构相关的上界。在GCR设计下，最著名的HT估计上界在度量结构的参数中是指数的，我们给出了在RGCR下的一个可比的上界，它在相同的参数下是多项式的。我们提供了大量的模拟来比较RGCR和GCR设计，观察到在各种设置下门估计的显著改进。
Abstract The global average treatment effect (GATE) is a primary quantity of interest in the study of causal inference under network interference. With a correctly specified exposure model of the interference, the Horvitz–Thompson (HT) and Hájek estimators of the GATE are unbiased and consistent, respectively, yet known to exhibit extreme variance under many designs and in many settings of interest. With a fixed clustering of the interference graph, graph cluster randomization (GCR) designs have been shown to greatly reduce variance compared to node-level random assignment, but even so the variance is still often prohibitively large. In this work, we propose a randomized version of the GCR design, descriptively named randomized graph cluster randomization (RGCR), which uses a random clustering rather than a single fixed clustering. By considering an ensemble of many different clustering assignments, this design avoids a key problem with GCR where the network exposure probability of a given node can be exponentially small in a single clustering. We propose two inherently randomized graph decomposition algorithms for use with RGCR designs, randomized 3-net and 1-hop-max, adapted from the prior work on multiway graph cut problems and the probabilistic approximation of (graph) metrics. We also propose weighted extensions of these two algorithms with slight additional advantages. All these algorithms result in network exposure probabilities that can be estimated efficiently. We derive structure-dependent upper bounds on the variance of the HT estimator of the GATE, depending on the metric structure of the graph driving the interference. Where the best-known such upper bound for the HT estimator under a GCR design is exponential in the parameters of the metric structure, we give a comparable upper bound under RGCR that is instead polynomial in the same parameters. We provide extensive simulations comparing RGCR and GCR designs, observing substantial improvements in GATE estimation in a variety of settings.
登录
查看更多内容
影响因子：
4.5
作者：
Sävje F;Aronow P;Hudgens M
通讯作者：
Hudgens M
DOI：
10.1145/3391403.3399507
发表时间：
2020
期刊：
ACM Economics and Computation (EC
影响因子：
--
作者：
Johari, Ramesh;Li, Hannah;Weintraub, Gabriel
通讯作者：
Weintraub, Gabriel
影响因子：
1.4
作者：
Chin, Alex
通讯作者：
Chin, Alex
DOI：
10.1073/pnas.2208975119
发表时间：
2022-11
影响因子：
11.1
作者：
通讯作者：
--