VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Seminar on Statistics: Bayesian Statistics
Seminar über Statistik: Bayesian Statistics
Last Updated: 2026-02-05 15:29:10
Abstract
The seminar discusses the Bayesian paradigm where also the unknown parameters are considered as random variables. Topics include prior, posterior and likelihood, differences to frequentist statistics, empirical Bayes procedures, nonparametric Bayesian methods, asymptotic properties of the posterior, model selection and computational methods.
Objective
The goal of the seminar is to familiarize participants with the paradigm of Bayesian statistics where not only observations, but also unknown parameters are considered as random variables. Their distribution describes the uncertainty about the values of these parameters, and Bayes formula describes how these distributions change on the basis of observations. Topics to be discussed are prior, posterior and likelihood, differences to frequentist statistics, hierarchical models and empirical Bayes procedures, nonparametric Bayesian methods, asymptotic properties of the posterior, model selection and BIC, computational methods and possibly de Finetti's theorem and axiomatic approaches to utility and uncertainty.
Resources
Literature
The main reference is the book Ch. Robert, The Bayesian Choice, 2nd ed. (2001), Springer NY. Additional material for the different lectures will be made available in the seminar.
General Information
- Language
- English
- Levels
- BSC , MSC
- Frequency
- Yearly recurring
Examination
- Type
- ungraded semester performance
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| seminar | Seminar über Statistik |
|
2 h weekly |