The content of this talk is fairly advanced but some of it will come in handy for subsequent parts of the course.
- How are steps chosen in an MCMC analysis?
- Give an example of a parameter you would estimate under each of the following prior distributions and try to state why?
- Gamma distribution
- Lognormal distribution
- Beta distribution
- Dirichlet distribution
- Why do we sometimes need to calculate the marginal likelihood?
- What is the difference between a hierarchical model and a non-hierarchical model?
- Briefly explain how stepping stones can be used to calculate the marginal likelihood (advanced).
Congratulations you’ve reached the end of some pretty advanced talks! Don’t worry if you didn’t understand everything, we’ll go over everything together in class!