Biostatistics Seminar Series - Yuanjia Wang, PhD

Title: Statistical Methods for Predicting COVID-19 Pandemic and Assessing Effects of Mitigation StrategiesAbstract: COVID-19 pandemic is the defining global health crisis of our time that has posed unprecedented challenges to the society. We discuss statistical methods to predict COVID-19 pandemic course and compare mitigation measures across states to inform decision making. We propose a robust and parsimonious survival-convolution model to forecast the disease epidemic. We account for transmission during a pre-symptomatic period and use a piece-wise infection rate function to reflect the temporal trend and change in response to a public health intervention. We estimate the intervention effect using a natural experiment design and quantify uncertainty by permutation. To compare state policies, we adjust for between-state differences in demographics, testing capacity, social economic vulnerability, and mobility. Our weekly realtime forecasts are included in the COVID ensemble modeling hub and CDC forecasts.