|
Lecturer(s)
|
|
|
|
Course content
|
Topics we will cover: - Data types and data sources - Probability, conditional probability and Bayesian inference - Bayesian networks and causal inference - Predictive modeling and its pitfalls - Evidence Based Medicine - Machine learning and its implications
|
|
Learning activities and teaching methods
|
|
Lecture, Dialogic Lecture (Discussion, Dialog, Brainstorming), Group work
|
|
Learning outcomes
|
The aim of the course is to teach students how to work with data and records, search for relevant data sources, distinguish between high- and low-quality data, and understand various data types (population-wide, survey-based, clinical studies, etc.). Furthermore, students will learn to identify valid versus invalid implications, understand the distinction between association and causality, grasp the pitfalls of predictive modeling, defend their perspective on a given issue with data-backed arguments, and recognize flaws in the arguments of others.
working with data and records finding data sources understanding types of studies understanding valid and invalid arguments understanding the difference between correlation and causality understanding predictive modeling
|
|
Prerequisites
|
Interest in the matter
|
|
Assessment methods and criteria
|
Student performance, Dialog, Final project
Credits for active participation, exam by scientific discourse
|
|
Recommended literature
|
-
Kahnemann, D. (2012). Thinking Fast and Slow. Penguin.
-
Pearl, J. (2008). The Book of Why. Basic Books.
-
Silver, N. (2015). The Signal and the Noise. Penguin Books.
-
Tetlock, P. (2016). Superforecasting. Crown.
|