Valen E. Johnson, "A coupling-regeneration scheme for diagnosing convergence in Markov chain Monte Carlo algorithms," Journal of the American Statistical Association, vol. 93, pp. 238--248, 1998. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A Bayesian Approach to Characterizing Uncertainty in Inverse.. - Higdon, Lee, Bi (2001) (1 citation) (Correct)
....the coarse and fine scale posterior realizations are quite similar. # 5 A. Coupled Markov chain Monte Carlo In order to link the coarse and fine scale formulations we employ the ideas from Metropolis coupled chains [3] Coupling ideas have been used previously for diagnosing convergence, e.g. [5], 6] as well as for improving mixing properties of MCMC chains [7] 8] However using coupling to link scales appears to be a novel approach which is hinted at in the rejoinder of [9] The basic idea is this: instead of running two separate MCMC chains, one on the fine parameter space and one ....
Valen E. Johnson, "A coupling-regeneration scheme for diagnosing convergence in Markov chain Monte Carlo algorithms," Journal of the American Statistical Association, vol. 93, pp. 238--248, 1998.
A process-convolution approach to modeling temperatures in the.. - Higdon (1998) (4 citations) (Correct)
....from it s full conditional distribution. One cycle of the Gibbs sampler consists of a single update to each of the parameters. Since the initial estimate is not necessarily a draw from the posterior, the chain is allowed to burn in until the stationary distribution is reached. Diagnostics from Johnson (1996) indicate the chain reaches the stationary distribution 12 0.135 0.140 0.145 0.150 0.155 0.160 0.165 0 100 200 300 400 sigma 2 e 0.65 0.66 0.67 0.68 0.69 0 200 400 600 800 mu x 0.26 0.28 0.30 0.32 0.34 0.36 0.38 0 100 200 300 400 500 sigma 2 x Figure 5: Histograms of the ....
Johnson, V. E. (1996) A coupling-regeneration scheme for diagnosing convergence in markov chain monte carlo algorithms, Technical Report 96-05, Institute of Statistics and Decision Sciences, Duke University.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC