A0350
Title: Parametric bootstrap on networks with non-exchangeable nodes
Authors: Can Minh Le - University of California, Davis (United States) [presenting]
Zhixuan Shao - University of California Davis (United States)
Abstract: The parametric bootstrap method for networks is studied to quantify the uncertainty of statistics of interest. While existing network resampling methods primarily focus on count statistics under node-exchangeable (graphon) models, more general network statistics are considered (including local statistics) under the Chung-Lu model without node-exchangeability. The natural network parametric bootstrap is shown to first estimate the network-generating model and then draw bootstrap samples from the estimated model generally suffers from bootstrap bias. As a general recipe for addressing this problem, it is shown that a two-level bootstrap procedure provably reduces the bias. This essentially extends the classical idea of iterative bootstrap to the network setting with a growing number of parameters. Moreover, the second-level bootstrap provides a way to construct higher-accuracy confidence intervals for many network statistics.
