| 52 | * Multidimentional MCMC |
| 53 | * component-wise mcmc/gibbs sampling |
| 54 | * Genotype freq. and inbreeding |
| 55 | * Simple component-wise M-H sampling |
| 56 | * propose-sample/reject each parameter individually |
| 57 | * Gibbs sampling (Full conditional distribution) |
| 58 | * Latent variables - missing data models. What data would you need in order to make it really easy to solve the problem? |
| 59 | * Distribution conditional on fixed state of all other parameters |
| 60 | * Gibb sampling is a special case of component-wise M-H sampling, conditional on all other parameters |
| 61 | * Wrap-up |
| 62 | * MCMC almost always proposes small changes to subsets of the variables |
| 63 | * Detailed balance, irreducible chain, latent variables |