Wastewater-based surveillance (WBS) has emerged as an important tool for monitoring infectious diseases at the community level, particularly when clinical testing is limited or delayed. By tracking viral signals in wastewater, public health agencies can obtain early indications of disease transmission and hospitalization trends. However, WBS data also introduce a range of unique statistical challenges, such as complex lag relationships, temporal dynamics, under-reporting of infections, and spatial dependence across health regions.

This talk discusses several statistical modeling approaches motivated by these challenges. I will discuss our recent work on modeling the lagged association between wastewater viral signals and hospitalizations, accommodating time-varying delay structures, jointly modeling multiple surveillance indicators under data aggregation and infection under-reporting, and incorporating spatio-temporal dependence in wastewater surveillance systems. The talk will highlight how statistical methods can contribute to the development of wastewater-based infectious disease monitoring.

报告人简介：Kangyi (Ken) Peng received his Ph.D. in Statistics from Simon Fraser University in 2025 under the supervision of Prof. Joan Hu and Prof. Tim Swartz. He is currently a postdoctoral researcher working with Prof. Robert Delatolla’s group at the University of Ottawa. He was awarded the Canadian Statistical Sciences Institute (CANSSI) Distinguished Postdoctoral Fellowship for the 2026–2028 cohort. His research focuses on statistical modeling for stochastic systems, with applications in wastewater-based infectious disease surveillance and sports analytics. His broader research interests include Bayesian statistics, latent variable modeling, spatio-temporal methods, and biostatistics.