Date: Friday, April 25, 2025
Time: 8:30 a.m.–5:00 p.m.
Place: Hybrid (in person and on Zoom); University of Manitoba, Fort Gary Campus, Armes Building, Room 200
This one-day workshop on “Processing and Forecasting with Epidemic Surveillance Data,” led by Daniel J. McDonald, Professor of Statistics at the University of British Columbia, is the third in the CANSSI Prairies Workshop Series in Data Science. We invite you to join us either in person or online.
Professor McDonald outlines his presentation as follows:
“In this workshop, I will demonstrate how to use R to load, process, inspect, and forecast aggregate epi surveillance data. I will be presenting a few case studies to motivate the entire pipeline from signal discovery to the production of nowcasts and forecasts. The focus will be on aggregate signals (not line list data), such as the counts of new hospitalizations per day per location. I will highlight three software packages our group is developing to aid in these tasks: epidat(r/py) for data acquisition, epiprocess for signal processing and exploration, and epipredict for producing forecasts. The sessions will include interactive worksheets and labs for hands-on practice. By the end, attendees will be equipped to produce forecasts for submission to the Canadian Respiratory ForecastHub.”
REGISTER ON EVENTBRITE (opening soon)
Daniel J. McDonald is Associate Professor of Statistics at the University of British Columbia in Vancouver. Before joining UBC, he spent 8 years on the faculty at Indiana University, Bloomington. Daniel did his undergraduate studies at Indiana University where he received a Bachelor of Science in Music with a concentration in cello performance from the Jacobs School of Music and a Bachelor of Arts in economics and mathematics. He received his PhD in Statistics in 2012 from Carnegie Mellon University, and his dissertation was awarded the Umesh Gavasakar Memorial Thesis Award. In 2017, he was a recipient of the Indiana University Trustees Teaching Award. In 2018, he received a National Science Foundation CAREER award.
Daniel’s methodological research involves the estimation and quantification of prediction risk, especially for complex dependent data. This includes the application of statistical learning techniques to time series prediction problems, as well as investigations of cross-validation for risk estimation. To promote adoption of these methods, he prioritizes open-source software development in R and lower-level languages, with packages available on CRAN, GitHub, and Bioconductor. On the applied side, previous work focussed on applications in economics, engineering, neuroscience and atmospheric science. Current work examines methods for understanding and modelling epidemiological data, especially forecasting, nowcasting, and software development with Carnegie Mellon University’s Delphi Research Group.
The CANSSI Prairies Workshop Series in Data Science offers an excellent opportunity for individuals to enhance their knowledge and skills in various areas of data science. Through a series of engaging and interactive hybrid (online and in-person) sessions, participants have the opportunity to explore new topics, learn cutting-edge techniques, and connect with experts in the field.