SBM: Main function of the Stochastic Block Model (SBM)
In drvalle1/EcoCluster: Bayesian Clustering using Truncated Stick-Breaking priors

Runs the Gibbs sampler and returns samples from the posterior distribution

1	SBM(dat, ngroup.loc, ngroup.spp, ngibbs, burnin)

`dat`	matrix has L rows (e.g., locations) and S columns (e.g., species), containing the presence-absence data
`ngroup.loc`	maximum number of location groups (KL)
`ngroup.spp`	maximum number of species groups (KS)
`ngibbs`	number of Gibbs sampler iterations
`burnin`	number of iterations to discard as part of burn-in phase

this function returns samples from the posterior distribution in the form of a list containing several matrices. These matrices have ngibbs-burnin rows and contain the posterior distribution for:

theta: probability of each location group
phi: probability of each species group
llk: log-likelihood for each iteration
psi: presence probability for each location group and species group
z: cluster assignment of each location
w: cluster assignment of each species
gamma: TSB prior parameters (one for location groups and the other for species groups)