About the workshop
Computational advances have made it possible to apply Bayesian statistical inference to analyze data in various real-world applications. Bayesian statistical methods show up in many applied fields, including biology, finance, earth sciences, and more. These methods allow us to take existing knowledge about an unknown parameter and update it as new data becomes available. In this way a distribution for population parameters can be constructed which can then be visualized to identify which values are most likely based on our data. Bayesian inference can be used for almost any research question where we already have some information about a parameter of interest.
This in-person workshop will give you a brief description of Bayesian statistical methods and introduce the Rstan package, an interface between the R programming language and Stan, a popular tool for creating and estimating models in the Bayesian framework.
The topics covered include:
- Review of the basics of maximum likelihood based statistics.
- Distinction between Bayesian and classical statistical methods, with the pros and cons of each approach.
- Review of Bayesian statistical method including prior, posterior inference, etc.
- Computation methods used for Bayesian estimation (i.e., Markov chain Monte Carlo or MCMC).
- Writing and estimating Bayesian models using Rstan and Rstanarm.
Requirements
Category