Fifth year Statistics Ph.D. student, Joshua Loyal, has been selected by the International Chinese Statistical Association (ICSA) as a recipient of the 2021 Applied Statistics Symposium poster award. Award consideration open for students, postdocs, junior faculty, or junior statisticians with PhD or terminal degree conferred in 2017 or later, who is also the first author of the poster. Loyal was one of six recipients of the award.
Loyal’s poster was titled: An Eigenmodel for Dynamic Multilayer Networks. Loyal is advised by Professor Yuguo Chen.
The abstract is as follows: Dynamic multilayer networks frequently represent the structure of multiple co-evolving relations; however, statistical models are not well-developed for this prevalent network type. Here, we propose a new latent space model for dynamic multilayer networks. The key feature of our model is its ability to identify common time-varying structures shared by all layers while also accounting for layer-wise variation and degree heterogeneity. We establish the identifiability of the model’s parameters and develop a structured mean-field variational inference approach to estimate the model’s posterior, which scales to networks previously intractable to dynamic latent space models. We demonstrate the estimation procedure’s accuracy and scalability on simulated networks. We apply the model to two real-world problems: discerning regional conflicts in a data set of international relations and quantifying infectious disease spread throughout a school based on the student’s daily contact patterns.
The 2021 ICSA Applied Statistics Symposium was held from September 12, 2021 to September 15, 2021 and was the 30th annual symposium for the ICSA. The theme for this year’s conference was Leading with Statistics and Innovation. More than 50 keynote speakers, senior invited speakers, ICSA leaders, Symposium committee members, senior statisticians, leaders and faculty members from academia, industry and government agencies served as judges for poster award competitions.