The MIDAS Webinar Series features research by MIDAS members, and is open to the public.
Date: Friday, March 29, 2024
Speaker: Matthew Wascher
Abstract: In this talk, I will describe a statistical methodology developed as part of the COVID-19 transmission monitoring efforts of The Ohio State University (OSU) and which is designed for monitoring disease transmission and prevalence in a closed population where individuals undergo repeated longitudinal testing and upon testing positive are subsequently isolated. We show that in this setting, naive estimation techniques may produce biased estimates of disease prevalence. Our method avoids this bias by incorporating a transmission model and using ideas from survival analysis. The other important feature of our method is that it allows for changes in transmission dynamics and human behavior through changes in the model parameters without rendering the model computationally prohibitive. We demonstrate the performance of our model on both synthetic data and real SARS-CoV-2 testing data collected at the OSU Columbus campus. This is joint work with Patrick Schnell, Wasiur Khudabukhsh, Greg Rempala, Joe Tien, and Mikkel Quam.
Bio: Matthew Wascher received his Ph.D. in Statistics from The Ohio State University and spent one year as a postdoctoral scholar at The Ohio State University Mathematical Biosciences Institute before joining the Department of Mathematics at the University of Dayton as an Assistant Professor of Statistics in 2021. His research interests lie in applications of probability and statistics to problems in biology and public health.