📝 SummarXiv

Abstract

Network interference amounts to the treatment status of one unit affecting the potential outcome of other units in the population. Testing for spillover effects in this setting makes the null hypothesis non-sharp. An interesting approach to tackling the non-sharp nature of the null hypothesis in this setup is constructing conditional randomization tests such that the null is sharp on the restricted population. In randomized experiments, conditional randomized tests hold finite sample validity and are assumption-lean. In this paper, we incorporate the network amongst the population as a random variable instead of being fixed. We propose a new approach that builds a conditional quasi-randomization test. To build the (non-sharp) null distribution of no spillover effects, we use random graph null models. We show that our method is exactly valid in finite samples under mild assumptions. Our method displays enhanced power over state-of-the-art methods, with a substantial improvement in cluster randomized trials. We illustrate our methodology to test for interference in a weather insurance adoption experiment run in rural China.