PhD course on Advanced Topics in Data Analysis

The Globe PhD course on Advanced Topics in Data Analysis is now open for enrollment. It is co-taught by Shyam Gopalakrishnan and Fernando Racimo, and will run from October 19th to October 30th. It is free for PhD students in Danish universities and you can sign up via this link.

ECTS: 5

Regular seats: 20

Content

This course is meant as an exposure to the state-of-the-art statistical techniques commonly used in life, environmental and earth sciences. It is a natural follow-up to the course on Fundamentals in Large-Scale Data Analysis offered within the “Life, Earth and Environmental Sciences” Programme.  In the first half of the course, the attendees will learn about the philosophy and techniques behind Bayesian thinking and inference, while also applying these methods on practical, real-world examples, using the R programming language. First, the students will be exposed to building, running and evaluating a model, including topics like posterior predictive checks, confounders, model evaluation and causal inference. In the second half of the course, the students will be introduced to machine learning techniques. We will provide a broad overview of machine learning methods, including random forests, support vector machines and deep learning, in various scientific applications. Finally, we will discuss various aspects of being a good data scientist, including the ethical and ecological implications of high-intensity scientific computing, data management and sharing.

Participants

The course is broadly meant for students in life, earth and/or environmental sciences who aim to develop their statistical and computational toolbox, in order to be able to tackle large-scale datasets. Students should have some background in basic probability, statistical inference and/or data science.

Course prerequisites

1. A basic understanding of probability theory and distributions.
2. The student must have taken the “Fundamentals in Large-Scale Data Analysis” course OR the student must have a waiver - by demonstrating their knowledge of the contents of the basic data analysis course. 
3. The student must have a working familiarity with the R environment or another similar language. The student must also be familiar with basic commands on the unix command line.