Topics in Longitudinal Data Science
Lecturer: Jan Beyersmann
Exercises: Judith Vilsmeier
English, unless all students have sufficient knowledge of German
Master students from one of the mathematical programs. You should at least have taken one class in either causal inference or
The aim of the lecture is to introduce students to current research topics in longitudinal data science, with an emphasis on applications in the life sciences. Take vaccination against COVID-19 as an example. The gold standard to demonstrate that a vaccine works is a randomized intervention. However, participants randomized to, say, experimental vaccination may not neccessarily adhere to the prescribed vaccination scheme. One question is how to adjust for such longitudinal non-compliance. Even more difficult are heterogeneous vaccination schemes using different vaccines. These are considered to be especially effective, but randomized interventions do not exist. We will, e.g., aim to tackle the latter question using causal counting process models. The lecture may lead to subsequent master theses.
Mainly research papers handed out during the course.
Both lectures and exercises will be on site. Further information will be available via the Moodle page of the course.
Password to Moodle page will be provided during the first lecture.