Timeline for Implementing MCMC
Current License: CC BY-SA 3.0
12 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 18, 2013 at 7:26 | comment | added | Toka Stall | Sorry for the ambiguity in my question. In my actual problem I have more than 1000 parameters, so MCMC is the way to go. Regarding the posterior conditionals, my intention (motivated by making the code much faster) was to use the same scheme for all subsequent iterations. Clearly this is wrong as explained... | |
| Aug 18, 2013 at 5:36 | comment | added | Glen_b | Dimitris - it might look like the two answers you have so far disagree, but it's not actually the case; they simply interpret the implications of your question differently. Mine takes your question to refer only to the first iterate, the other takes the same scheme to refer to all subsequent iterates as well. | |
| Aug 18, 2013 at 5:31 | comment | added | Glen_b | @DavidMarx I think probabilityislogic is suggesting that it is better to use MCMC on large problems rather than very small problems that can be done to high accuracy in other ways. | |
| Aug 18, 2013 at 5:02 | comment | added | David Marx | @probabilityislogic MCMC works fine for arbitrary number of parameters. Otherwise hierarchical models wouldn't work very well, since you generally need to track the posteriors for multiple parameters at each level of the model. Hell, bayesian linear regression wouldn't work either sinec you'd need to track the posterior of each coefficient. | |
| Aug 18, 2013 at 3:46 | comment | added | probabilityislogic | @Glen_b - I take your point, but there's nothing explicitly in the question that says this is a pure learning exercise. If it is a "real" problem, then mcmc would be crazy for a two parameter problem. MCMC should always be the method of last resort imo. | |
| Aug 18, 2013 at 2:57 | answer | added | guy | timeline score: 5 | |
| Aug 18, 2013 at 2:48 | comment | added | Glen_b | @probabilityislogic when first learning MCMC it's often worth starting on problems you can check the answers to. | |
| Aug 18, 2013 at 0:30 | comment | added | probabilityislogic | Not exactly related, but I wouldn't use MCMC for a two parameter problem. Quadrature would be much better. | |
| Aug 17, 2013 at 21:34 | answer | added | Glen_b | timeline score: 3 | |
| Aug 17, 2013 at 21:29 | history | edited | Glen_b | CC BY-SA 3.0 |
fixed spelling, LaTeX formatting, added tag
|
| Aug 17, 2013 at 21:16 | review | First posts | |||
| Aug 17, 2013 at 21:30 | |||||
| Aug 17, 2013 at 21:00 | history | asked | Toka Stall | CC BY-SA 3.0 |