Bayesian computation
via Monte Carlo methods: A brief introduction
VI Congreso Bayesiano de America
Latina - VI COBAL
Lima, Peru, Junho 2019
Hedibert Freitas Lopes
Professor of Statistics
and Econometrics
Insper Institute of Education and Research
URL: www.hedibert.org
E-mail: hedibertfl@insper.edu.br
Outline of the tutorial
Part 1: Bayesian
ingredients
Part 2: Monte Carlo
methods
Part 3: Markov Chain
MC methods
Part 4: Stochastic
volatility models
Part 5: Sequential
Monte Carlo (pure filter)
Part 6: Sequential
Monte Carlo (parameter learning)
Additional material
Comparing
MC integration, SIR and Raoblackwellization
Finite
Mixture of Poisson Distributions (Rmarkdown)
AR(1)
plus noise model: block-move versus single-move
Hidden
Markov Model: variance-switching (Rmarkdown)