Fit the hidden Potts model using a Markov chain Monte Carlo algorithm.
mcmcPotts(y, neighbors, blocks, priors, mh, niter = 55000, nburn = 5000, truth = NULL)
| y | A vector of observed pixel data. |
|---|---|
| neighbors | A matrix of all neighbors in the lattice, one row per pixel. |
| blocks | A list of pixel indices, dividing the lattice into independent blocks. |
| priors | A list of priors for the parameters of the model. |
| mh | A list of options for the Metropolis-Hastings algorithm. |
| niter | The number of iterations of the algorithm to perform. |
| nburn | The number of iterations to discard as burn-in. |
| truth | A matrix containing the ground truth for the pixel labels. |
A matrix containing MCMC samples for the parameters of the Potts model.