Bayesian Monitoring of a Pandemic: A Case Study
As pandemics unfold regulators, health professionals and politicians want to understand how the pandemic is progressing. Specifically, how the underlying dynamics of the pandemic are changing (or
hygiene, etc a dynamic approach to modeling the parameters of the pandemic through time is needed. A dynamic sampling regime is implemented which allows for both parameter estimation as well as uncertainty quantification to allow the parameters to vary through time and hence overcoming the steady state assumptions. Furthermore, these parameters can be monitored through time using an Multivariate Exponentially Weighted Moving Average approach which will signal when the parameters of the underlying model have changed. This signal will allow stakeholders to take action, where necessary. The method is illustrated using the COVID-19 data from the State of Qatar.
Speaker Biography
Prof. Edward L. Boone is a Full Professor in the Department of Statistical Sciences and Operations Research at Virginia Commonwealth University. He earned his BS in Mathematics Education from Bowling Green State University, an MS in Mathematics from Miami University, and an MS and PhD in Statistics from Virginia Polytechnic Institute and State University (Virginia Tech). He has a passion for Applied Bayesian Statistical Methodology and has worked with researchers in fields such as Forensic Science, Fisheries, Biology, Genomics, Metabolomics, MRI image analysis, Toxicology, Environmental Science and Neurology. As applied work requires collaboration he has developed collaborations with researchers in the USA, Australia, UK, Italy and multiple projects across universities in Qatar. In addition, he brings these research collaborations into the classroom and eagerly seeks to include both