Gracia Dong
Gracia Dong is a CANSSI Distinguished Postdoctoral Fellow for 2022–2024.

Gracia Dong Takes On the Challenge of “Estimating COVID-19 Prevalence in Homeless Populations”

Gracia’s project involves developing novel statistical Bayesian models for estimating the prevalence of COVID-19 in hidden or marginalized populations. Specifically, Electronic Health Records (EHR) will be used to obtain estimates for COVID-19 prevalence in homeless populations on Vancouver Island. She will develop capture-recapture methods and methods of inference and will address problems in the data provided.

Program: CANSSI Distinguished Postdoctoral Fellowship
Region: National
Date: 2022–2024

Project Focus Areas

Available incidence and prevalence data on an emerging infectious disease (EID) during a pandemic is bound to be incomplete and biased. The proportion of infected individuals who are tested varies over time, geographically and by ethnic group. Obtaining an accurate picture of the extent of an EID in the population, and the various sub-populations which are most severely affected, requires complex modelling of existing data sources and innovative data collection strategies.

This specific project proposal involves using multiple-system estimation methods to estimate the prevalence of COVID-19 in the homeless population. This method is commonly used in ecology and epidemiology to estimate a population size when it is impractical to count every individual. Using data linked from Electronic Health Records, one can capture the proportion of individuals with COVID-19 without a registered home address as well as employment status.

Gracia’s current research aims to answer the question ‘Do health data records contain the information we need to estimate homeless populations?’ She is developing statistical methods to enumerate hidden-populations using open population capture-recapture models (Dam-Bates et al. 2016) and developing tools to roll these methods out to the large data environment of health data records in collaboration with the Vancouver Island Health Authority to estimate the abundance of homeless populations on Vancouver Island.

This project will help expand the scope of the Statistical Methods for Managing Emerging Infectious Diseases (SMMEID) network for which NSERC has granted funding.

Other projects involve quantifying the association between temperature and air pollution and health effects using case-crossover models, and finding disparities and inequities in access to services for marginalized groups using longitudinal encounter data.

Laura Cowen, Patrick Brown, Gracia Dong
From left: Laura Cowen, Patrick Brown, and Gracia Dong.

Getting to Know Gracia

Gracia’s graduate research program was based on quasi-Monte Carlo (QMC) methods and computation statistics, with a focus on QMC for high-dimensional function estimation and error reduction for numerical integration. Her work involved showing the negative dependence properties of (t, m, s)-nets as well as point sets based on the Halton sequence. She also worked on applications of these point sets: creating point sets on triangles and the surfaces of spheres based on the scrambled Halton sequence.

During her graduate studies in statistics at the University of Waterloo, Gracia become passionate about applying statistics to other fields as well as sharing that passion with others through teaching. Her specialization is in computational statistics, and she loves being able to use her skills to solve real-life problems.

Gracia believes that the CANSSI Distinguished Postdoctoral Fellowship will help her achieve her goals by letting her build her network with researchers at two different universities and providing her with opportunities to improve her teaching and leadership skills.

As a recipient of the CANSSI Distinguished Postdoctoral Fellowship, Gracia will work under the supervision of Laura Cowen at the University of Victoria and Patrick Brown at the University of Toronto.

When I teach, one of the most enjoyable aspects is watching a student realize that that what they’re learning is quite enjoyable and has many interesting applications beyond the classroom. By working on such interesting applications that impact real people, I will be able to use my experiences in the future when teaching to motivate my students.

About the Supervisors

Laura Cowen

Laura Cowen is a professor in the Department of Mathematics and Statistics at the University of Victoria (British Columbia).

She is an ecological statistician studying animal demography, in particular through capture-recapture methods and applications. She has worked on human, fishery, aquaculture, and seabird populations estimating population parameters such as survival and abundances and developing statistical methods to provide these estimates. She also collaborates with other scientists (such as ecologists, fisheries scientists, microbiologists, seabird biologists) to work on ecological problems in the broader sense. Finally, she collaborates with sociologists and anthropologists looking at aspects of injection drug user populations and modelling lemur populations.

Patrick Brown

Patrick Brown is an associate professor in the Department of Statistical Sciences at the University of Toronto with a cross-appointment at the Centre for Global Health Research at St Michael’s Hospital in Toronto.

His research focuses on models and inference methodologies for spatio-temporal data, motivated by problems in spatial epidemiology and the environmental sciences. Current statistical methods research involves Bayesian inference for non-Gaussian spatial data, and non-parameteric methods for spatially aggregated and censored locations.

Explore More Stories

Find Related Programs

“Estimating COVID-19 Prevalence in Homeless Populations” is a CANSSI Distinguished Postdoctoral Fellowship (CDPF) project. The CDPF is a two-year program that includes a substantial research project, applied interdisciplinary collaboration, and teaching experience.

CANSSI Distinguished Postdoctoral Fellowships are supported by a competitive salary. They provide opportunities for professional development and prepare postdoctoral fellows for success in a variety of careers.