Justin Slater

Headshot of Dr. Justin Slater
Assistant Professor
Department of Mathematics and Statistics
Email: 
jslate04@uoguelph.ca
Office: 
MACN 521
Seeking academic or industry partnerships in the area(s) of: 
Statistics, Infectious disease, health data science, health services research, population health
Available positions for grads/undergrads/postdoctoral fellows: 
Please refer to Prof. Slater’s website for open positions

Education and Employment Background

Prof. Slater will complete his Ph.D. in early 2023 from the Department of Statistical Sciences at the University of Toronto. Prior to this, he worked as a statistical consultant at Cytel Inc, and an analyst at the Institute for Clinical Evaluative Sciences. Justin also holds an M.Sc. in Statistics (Queen’s) and an Honours B.Sc. in Math and Statistics (Dalhousie).


Research Themes

Prof. Slater’s research interests span a wide spectrum of subfields including (bio)statistics, data science, and epidemiology. 

Key areas of focus include:

  1. Infectious disease statistics – Prof. Slater develops methods for modelling and understanding infectious disease spread. His current work aims to develop statistical analogues to differential equation models that are popular in mathematical biology. This will allow statisticians and epidemiologists to more accurately model epidemics, accounting for uncertainty from various sources.
  2. Spatio-temporal analytics – The key theme of our Master of Data Science here at Guelph, Prof. Slater is looking to train the next generation of spatial data scientists. Spatial methods are vital in epidemiology, tech, agriculture, veterinary sciences and more. His current research involves using cellphone-derived mobility data in spatio-temporal models for infectious diseases. 
  3. Bayesian statistics – Although not a Panacea, Bayesian statistics has several advantages when making decisions in the real world. Specifically, Prof. Slater is interested in prior elicitation to improve inference and computation, and leveraging Bayesian hierarchical models in data sparse contexts. In the coming years, he hopes to develop principled priors for infectious disease models and Bayesian mixture models.
  4.  Evidence synthesis – Making important decisions often involves combining many data sources, which often have different study populations and designs. Going forward, Prof. Slater looks to improve upon meta-analytic and adaptive clinical trial methods for combining evidence from randomized (e.g clinical trials) and non-randomized (e.g observational) studies. 

Highlights 

  • NSERC Postgraduate Scholarship – Doctoral (PGS-D 2021)