Bayesian back-calculation and nowcasting for line list data during the COVID-19 pandemic

Surveillance is the key of controling the COVID-19 pandemic, and it typically suffers from reporting delays and thus can be misleading. Previous methods for adjusting reporting delays are not particularly appropriate for line list data, which usually have lots of missing values that are non-ignorable for modeling reporting delays. In this paper, we develop a Bayesian approach that dynamically integrates imputation and estimation for line list data. We show this Bayesian approach lead to accurate estimates of the epidemic curve and time-varying reproductive numbers and is robust to deviations from model assumptions. We apply the Bayesian approach to a COVID-19 line list data in Massachusetts and find the reproductive number estimates correspond more closely to the control measures than the ones based on the reported curve.