±«ÓãÖ±²¥

Harlan Campbell, PhD

Postdoctoral Research Fellow | Department of Statistics | University of British Columbia

Where: Virtual |

Abstract

Estimating the COVID-19 infection fatality rate (IFR) has proven to be particularly challenging –and rather controversial– due in large part to the fact that both the data on deaths and the data on the number of individuals infected are subject to many different biases. In this presentation, I consider a Bayesian evidence synthesis approach which, while simple enough for researchers to understand and use, accounts for many important sources of bias and uncertainty inherent in both the seroprevalence and mortality data. With the understanding that the results of one's evidence synthesis may be largely driven by which studies are included and which are excluded, two separate parallel analyses are conducted based on two different lists of eligible studies. The various challenges encountered in estimating the COVID-19 IFR provide valuable lessons for epidemiologists conducting evidence synthesis with challenging data.

Learning Objectives

• Understand the various challenges of working with COVID-19 seroprevalence and mortality data and how these challenges can, to a certain degree, be addressed with Bayesian methods
• Discuss how the results of one's evidence synthesis analysis can be greatly impacted by which studies are included and which are excluded. It is therefore important to determine the how the uncertainty inherent in one’s risk of bias assessment can impact parameter estimates
• Describe how the lethality of COVID-19 likely varies with population age, wealth, and other factors which remain poorly understood, even today

Speaker Bio

Harlan Campbell is a statistician and is currently working as a postdoctoral research fellow in the Department of Statistics at the University of British Columbia. His work focuses on developing statistical methods with a wide range of applications including in clinical trials, epidemiology, ecology, and psychology. He is also interested in better understanding the parallels between frequentist and Bayesian paradigms, and in addressing the so-called reproducibility crisis. He earned his PhD in statistics at the University of British Columbia, after completing his masters at Simon Fraser University, and his undergraduate studies at ±«ÓãÖ±²¥.

Presented as part of the Epidemiology Seminar Series

The Department of Epidemiology, Biostatistics and Occupational Health Seminar Series is a self-approved Group Learning Activity (Section 1) as defined by the maintenance of certification program of the Royal College of Physicians and Surgeons of Canada