Loading...
Please wait, while we are loading the content...
Similar Documents
Cs294-2 Markov Chain Monte Carlo: Foundations & Applications 2.1 Applications of Markov Chain Monte Carlo (continued) 2.1.1 Statistical Inference
| Content Provider | Semantic Scholar |
|---|---|
| Author | Stauffer, Alexandre |
| Copyright Year | 2006 |
| Abstract | where Pr(Θ) is the prior distribution and refers to the information previously known about Θ, Pr(X | Θ) is the probability that X is obtained with the assumed model, and Pr(X) is the unconditioned probability that X is observed. Pr(Θ | X) is commonly called the posterior distribution and can be written in the form π(Θ) = w(Θ)/Z, where the weight w(Θ) = Pr(X | Θ)Pr(Θ) is easy to compute but the normalizing factor Z = Pr(X) is unknown. MCMC can then be used to sample from Pr(Θ | X). We can further use the sampling in the following applications: |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.stat.columbia.edu/~liam/teaching/neurostat-spr11/papers/mcmc/sinclair-MC-notes.pdf |
| Alternate Webpage(s) | http://www.stat.columbia.edu/~liam/teaching/neurostat-fall13/papers/mcmc/sinclair-MC-notes.pdf |
| Alternate Webpage(s) | http://www.stat.columbia.edu/~liam/teaching/neurostat-fall14/papers/mcmc/sinclair-MC-notes.pdf |
| Alternate Webpage(s) | http://www.stat.columbia.edu/~liam/teaching/neurostat-fall15/papers/mcmc/sinclair-MC-notes.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
