This course explores the philosophical and methodological foundations of quantitative research. We begin by examining frequentist assumptions of probability and statistical
inference, highlighting their limitations (e.g. Bernoulli’s fallacy) in empirical research. Building on this critique, the course introduces a Bayesian perspective on probability as degrees of belief, emphasizing entropy as a measure of uncertainty and data as information. Students will learn how Bayesian updating provides a coherent framework for research design, statistical inference, and causal analysis. The course concludes with an introduction to Bayesian econometrics, causal inference, and, if time permits, hierarchical modeling. Hands-on exercises and applied examples will be implemented in R.
- begleitende Lehrperson: Spencer Alexander Brown
- begleitende Lehrperson: Katharina Preuß
- verantwortliche Lehrperson: Jan David Weber