Cascade-based Randomization for Inferring Causal Effects under Diffusion Interference

arXiv:2405.12340v1 Announce Type: new
Abstract: The presence of interference, where the outcome of an individual may depend on the treatment assignment and behavior of neighboring nodes, can lead to biased causal effect estimation. Current approaches to network experiment design focus on limiting interference through cluster-based randomization, in which clusters are identified using graph clustering, and cluster randomization dictates the node assignment to treatment and control. However, cluster-based randomization approaches perform poorly when interference propagates in cascades, whereby the response of …

abstract arxiv assignment behavior causal cluster cs.lg cs.si current design diffusion effects experiment focus interference network nodes randomization through treatment type