A0715
Title: Accurate two-sample inference for network data
Authors: Yuan Zhang - The Ohio State University (United States) [presenting]
Abstract: A method is proposed to compare two networks' structures by the method of moments. The novel procedure is highly accurate and computationally efficient. The test achieves strong theoretical guarantees, namely, optimal separation condition under alternative hypothesis and higher-order accurate type I error rate, without needing resampling or making strong assumptions on knowledge about population distributions. We will showcase some simulations and real-life data applications.
