We are often confronted with seemingly clear empirical facts that we interpret as obvious causal relations between two or more empirical factors. For example, an increase in revenues of a firm after the change of the CEO is likely to be causally related to the CEO-change. Is this really the case? Or do we have to look for different causes of these relations?
There exist many statistical pitfalls and fallacies that we tend to overlook, or are even unaware of, in everyday life. This course introduces students to these pitfalls and enables them to read statistical arguments critically. Covering key areas of where statistical claims can ‘go wrong’ – that is, where false conclusions tend to be drawn from seemingly self-evident data – the course sharpens students’ analytical capabilities, allowing them to make better decisions in their professional career.
- Encouraging students not to take every empirical or statistical claim for granted
- Equipping students with the skills to critically evaluate these claims.
- Using analytical and logical thinking to achieve these goals – almost completely without stepping deeply into mathematics
The course consists of seminars. It is a practice-based course, where students participate in experiments or solve in-class exercises, either individually or in small groups.
Attendance is of course appreciated, but not required, except for the group work, see below.
- There will be a final assignment. The final assignment is an exam on the topics discussed in class.
- There will be an in-class group work
- Group work counts for 30% of the grade, while the final assignment counts for 70% of the grade