Center for Social Data Analytics Colloquium

Google map

The Center for Social Data Analytics will be hosting  Tianxi Li,  Assistant Professor in the School of Statistics at the University of Minnesota. His talk will be held on Friday, March 15 at 12:15 pm in B001 Sparks (the databasement), located 1 flight below classroom 10. His talk is titled: "Advancing Network Analysis: Novel Statistical Tools and Their Applications in Social Problems". 

Bio: Dr. Tianxi Li is currently an assistant professor in the School of Statistics at the University of Minnesota. He earned his Ph.D. in Statistics from the University of Michigan in 2018. Following his doctoral studies, Dr. Li joined the University of Virginia as an Assistant Professor, a position he held from 2018 to 2023. His research primarily focuses on statistical network analysis and high-dimensional statistical learning. Dr. Li received the New Researcher Award from the International Chinese Statistical Association (ICSA) in 2019.

Abstract: Social networks offer a rich vein of data for exploring human interaction and relational dynamics, presenting an invaluable complement to traditional multivariate datasets in the social sciences. These networks open up novel perspectives and methodologies for uncovering key insights into a wide array of social science challenges. However, the inherent complexities of social network data also introduce a set of unique analytical challenges, necessitating the development of innovative statistical tools to conduct robust and principled analysis. In this talk, I will highlight several recent advancements made by my research group in creating statistical tools tailored for various network analysis tasks that address social issues. Our discussion will cover techniques for analyzing networks characterized by informatively missing edges, methods for comparative inference across multiple unlabeled networks, and strategies for constructing generalized linear models capable of making inferences within noisy network structures. The practical applications of these methods will be illustrated through case studies focused on analyzing faculty hiring networks among academic institutions and student friendship networks in the context of school conflict studies. These examples serve to demonstrate how the integration of social network data enriches our analytical toolkit, enabling a deeper understanding of complex social phenomena.