11. Objective Bayes inference and MCMC Flashcards
1
Q
What are the problems of: Bayesian inference
A
- In the absence of relevant past experience, the prior may have an unwanted
subjective role. - Numerical calculations often involves intricate high-dimensional integrals.
2
Q
Recall the bayesian setting:
A
given a parametric model:
3
Q
How to choose g(µ)?
A
A: We’ll focus on uninformative priors
4
Q
Q: How to evaluate integrals over the posteror such as E{µ|x}?
A
A: Markov Chain Monte Carlo (MCMC).
5
Q
What is a flat prior?
A
For a finite space it is 1/k, all samples have the same prob
6
Q
Fisher claims a flat prior does not have a transfomration invariance, what was his solution?
A
Jeffreys prior
7
Q
What are cunjgate priors?
A
They are priors such that they will a posterior from the same family.
8
Q
Explain what n+ and x+ mean.
A
x+ = Its the update of the mean of the observation, its a fraction of the hypothetical observations of all of those, that is the weight of x0 and the mean of x
9
Q
A
