“Summer School” offers crash course in data science

What do researchers in molecular medicine, linguistics, astrophysics, finance, and nearly every other discipline have in common?  In one form or another, they all work with data.

Recently, more than 100 McMaster graduate students, postdoctoral fellows, and research associates from all Faculties gathered for the inaugural MacDATA Summer School in Data Science, a week of programming that provided participants with the opportunity to explore new ways of analysing and representing data.

Hosted by McMaster’s MacDATA Institute, the Summer School introduced participants to a range of data science tools and methodologies and looked at how these approaches could be applied to many different research projects.

“Most people aren’t exposed to data science – you could go though most graduate programs and not see it,” says Paul McNicholas, Tier 1 Canada Research Chair in Computational Statistics and the director of McMaster’s MacDATA Institute.

“People all over campus are working with different data types and there is likely a method they could be using that would help them get more from their data, but they may not know it’s possible,” he continues. “I hope the summer School will help introduce them to some of these approaches.”

Throughout the week, participants heard from data science experts from McMaster and beyond on a range of topics including applied analytics, data security, data visualization, data ethics, machine learning, optimization, statistical learning, text analytics, and programming languages including R, Python and Julia.

Instructors included, Antoine Deza and Reza Samavi, both from McMaster’s Department of Computing and Software, McNicholas, Peter Tait and Yang Tang, all from Mathematics and Statistics, Claudia Emerson, director of McMaster’s Institute on Ethics & Policy for Innovation, Andrew McArthur and Kara Tsang, from Biochemistry and Biomedical Science, Manaf Zargoush from the DeGroote School of Business, among others.

McNicholas says MacDATA plans to run the Summer School again, and a recently-signed MOU will see MacDATA and the Canadian Statistical Sciences Institute (CANSSI) partner on the development of future programming and events related to data science, such as the Summer School. Nancy Reid, the scientific director of CANSSI, delivered a special lecture, “In Praise of Small Data: Statistical and Data Science,” as part of this year’s Summer School programming.

“We’re excited to partner with MacDATA in advancing the national agenda in statistical and data science,” says Reid, Canada Research Chair in Statistical Methodology at the University of Toronto.

“CANSSI’s mission is to develop collaborations in both research and training that link statistical and data science to academia, government and industry,” she continues. “MacDATA’s Summer School, with its emphasis on participation across the campus, is an excellent example of the type of outreach that is at the heart of this mission. We hope it can serve as a model for similar activities across the country.”

The MacData Institute was created to identify synergies to foster collaboration among McMaster University’s institutes, centres, and researchers whose work involves the many facets of data. 

MacDATA Graduate Fellowship applications are now open. Learn more or apply.