Statistical Data Science

Managers, practitioners and researchers are, now more than ever, interested in extracting knowledge from data. However, as our appetite for answering more challenging questions grows, so does the complexity of the corresponding data analytics. Modern applications involving big data and/or complex mathematical models motivate the development of innovative data-focussed solutions that exploit the strengths of several quantitative fields, such as mathematics, statistics, machine learning and computer science. Data science is a broad term that encapsulates the use of at least one, often multiple, of these disciplines for solving problems informed by data.

The focus of this Winter School is on data science, skewed towards methods on the statistical side of the spectrum, but where skills in modern computing, machine learning and/or mathematics remain crucial. Attendees will learn about methods for fitting complex mathematical models to data, and extracting insight from big and challenging data sets. Specifically, the School will feature modules on Bayesian statistics, advanced Markov chain Monte Carlo methods, likelihood-free inference, dimension reduction for high dimensional data, and neural networks and related models.