Gibbs/Metropolis-Hastings Sampler Algorithm |
1) Initialize 2) Based on Metropolis-Hastings, create 3) Based on Metropolis-Hastings, create 4) Based on Metropolis-Hastings, create 5) Calculate 6) Put 7) Repeat steps (2 - 5) N times. 8) We get the point estimation by Bayes MCMC of
where M is the number of iterations (burn-in period) before the stationary distribution is accomplished and posterior variance of
9) The quintiles of the pattern are picked as the endpoints of the interval to calculate the reliable intervals of
|