MATH-339 / 5 crédits

Enseignant: Wang Sixuan Sven

Langue: Anglais


Summary

A first introduction to Bayesian statistics, assuming knowledge from first courses in statistics and probability. We will focus on foundational statistical and mathematical aspects such as the decision theoretic background, consistency for large sample sizes, and algorithms for Bayesian computation.

Content

Probabilistic foundations and the Bayesian paradigm

  • Bayes's formula
  • Bayesian estimation, testing and credible regions

Decision-theoretic foundations

  • Minimax and Bayes methods, admissibility
  • Complete class theorem

Conjugate models

Frequentist analysis of Bayesian methods

  • Consistency of Bayesian methods
  • Bernstein-von Mises theorem

Bayesian computation via Monte Carlo methods

  • Introduction to Markov Chains
  • Markov Chain Monte Carlo (MCMC) algorithms

Relevant literature:

  • Aad van der Vaart, Botond Szabo: Bayesian Statistics
  • Christian Robert: The Bayesian Choice (2007)
  • Peter Hoff: A First Course in Bayesian Statistical Methods (2009)

Keywords

Bayes' theorem
Decision theory
Minimax estimation theory
Bernstein-von Mises theorem
Markov Chain Monte Carlo (MCMC)
Bayesian computation

 

Learning Prerequisites

Required courses

Introductory courses in statistics and probability are necessary. Knowledge of measure-theoretic probability is beneficial.

Assessment methods

Written exam

Resources

Moodle Link

Dans les plans d'études

  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bayesian statistics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bayesian statistics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bayesian statistics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Exercices: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel

Semaine de référence

Cours connexes

Résultats de graphsearch.epfl.ch.