Teaching & Mentoring
2025–2026
Statistical Methods - STA272H1S (co-taught with Meredith Franklin)
Winter 2023
Introductory Computation and Data Science for the Social Sciences (GGR274)
Winter 2022
Previous Courses
An Introduction to Statistical Reasoning and Data Science - STA130
Design Of Scientific Studies - STA305
Data Science Methods, Collaboration, and Communication - STA2453
Introduction to Statistical Methods and Ideas - STA220
Student Research and Mentoring
Faculty mentor, University of Toronto Statistics Summer Research Program (UTSSRP), 2025: open-source teaching repositories on Nobel Prize winners and a Causal Inference Crash Course.
Supervisor, Data Sciences Institute SUDS undergraduate research (fine-tuning LLMs for clinical research), 2025.
Co-supervisor, AI-supported autograding and feedback in MarkUs (ASIP), 2025.
Supervisor of seven Master of Science in Applied Computing (MScAC) industry internships, 2016–2020.
Short Courses and Workshops
Crash Course on Causal Inference. University of Toronto Statistics Summer Research Program (UTSSRP), Summer 2025.
Teaching Data Science in the Cloud. Computation and Data Science Education Community of Practice, University of Toronto, September 2022.
Incorporating Cloud Computing into a Statistics Course. Statistical Society of Canada, Webinar on Teaching Statistics Online, June 2020.
Virtual Workshop on Analysis of Unstructured Text Data SSC - Data Science and Analytics Section - Spring 2020. Developed jointly with Dave Campbell.
DHSI Summer Institute: 2017 and 2018. Introduction to Machine Learning in the Digital Humanities. Developed jointly with Paul Barrett.
Data Science Contests
I have been involved in developing and organizing several data science contests, including ASA DataFest@UofT, and DataFest: COVID-19 Virtual Data Challenge.
During the 2019 Statistical Society of Canada Annual Meeting in Calgary, Alberta, I gave a presentation on ASA DataFest and Beyond (slides, handout on hosting a data science contest.) These resources may be helpful if you are thinking about organizing a DataFest contest at a university.
Experiential Learning
A Data Science contest is one way students are able to gain practical data science experience during university. This paper I presented at the 10th International Conference on Teaching Statistics (ICOTS10) outlines other possibilities.
My Teaching Philosophy in a Nutshell
I try to convey my enthusiasm for statistics and data science, so students can develop and build their interest in the subject. If I'm not excited by the material, then it's unlikely that students will become engaged. So, I always try to teach a class that I would like to attend as a student.
Teaching a class that is engaging, yet leads to a deeper understanding of statistics, requires presenting material that involves interesting stories and meaningful applications. I often try to incorporate my experiences as a consultant statistician from areas such as medical research and international law. It’s really important for students to experience practical aspects of statistics such as: data collection, data wrangling or evaluation of the validity of a conclusion based on a statistical analysis.
Striking a balance between the underlying mathematical concepts and the big picture so that students learning difficult statistical ideas remain engaged is crucial. Jordan Ellenberg, in How Not To Be Wrong, decries the myth that, only "mathematical geniuses” are capable of sound statistical reasoning. This myth not only discourages students from pursuing careers in the field, but future writers, doctors, high school teachers, and politicians from majoring in statistics or data science.
Generative AI is changing how students learn to code and analyze data. I see it as a reason to focus teaching on the human parts of data science: asking good questions, judging evidence and communicating results.