Mixture Normal Distribution for Gibbs Sampler and its Application in the Surface of Single Crystal

Abstract:

Gibbs sampler is widely used in Bayesian analysis. But it is often difficult to sample from the full conditional distribution, and this hardly weakens the efficiency of Gibbs sampler. In this paper, we propose to use mixture normal distribution for Gibbs sampler. The mixture normal distribution can approximate the target distribution. So carrying more information from target distribution, the mixture normal distribution tremendously improves the efficiency of Gibbs sampler. Further more, combining with mixture normal method, Hit-and-Run algorithm can also get more efficient sampling results. Simulation results show that Gibbs sampler with mixture normal distribution outperforms other sampling algorithms. The Gibbs sampler with mixture normal distribution can also be applied to explorer the surface of single crystal.

• Periodical: Advanced Materials Research (Volume 529)
• Pages: 585-589
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.529.585
• Online since: June 2012
• Authors: Wei Shao, Guo Qing Zhao, Yu Jie Gai
• Keywords: Gibbs Sampler, Hit-and-Run Algorithm, Markov Chain Monte Carlo, Mixture Normal Distribution, Surface of Single Crystal

References

[1] M. H. Chen and B. Schmeiser: Performance of the Gibbs, Hit-and-Run, and Metropolis samplers. Journal of Computational and Graphical Statistics. 2: 251-272. (1998).

DOI: 10.2307/1390645

[2] G. S. Fishman: Monte Carlo: concepts, algorithm, and applications. Springer. New York. (1995).

[3] A. Gelmen, G. O. Roberts and W. R. Gilks: Efficient Metropolis jumping rules. Bayesian Statistics. 5: 599-607. (1996).

[4] C. J. Geyer: Markov Chain Monte Carlo maximum likelihood. Computing Science and Statistic: The 23th symposium on the interface. 156-163. (1991).

[5] W. Hardle, M. Muller, S. Sperlich and A. Werwatz: Nonparametric and Semiparametric Models. Springer. New York. (2004).

[6] J. D. Hart: Nonparametric Smoothing and Lack-of-Fit Tests. Springer. New York (1997).

[7] W. K. Hastings: Monte carlo sampling methods using markov chains and their applications. Biometrika. 57: 97-109. (1970).

DOI: 10.1093/biomet/57.1.97

[8] F. M. Liang, G. H. Liu, and R. J. Carrol: Advanced Markov Chain Monte Carlo methods: learning from past samples. Wiley, New York. (2010).

DOI: 10.1002/9780470669723

[9] F. M. Liang and H. W. Wong: Real-parameter evolutionary Monte Carlo with application to Bayesian mixture models. Journal of the American Statistical Association. 95: 121-134. (2001).

DOI: 10.1198/016214501753168325

[10] J. S. Liu: Monte Carlo strategies in scientific computing. Springer. New Youk. (2001).

[11] N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth MN,A. H. Teller, and E. Teller: Equations of state calculations by fast computing machines. Journal of Chemical Physics. 21: 1087-1091. (1953).

DOI: 10.1063/1.1699114

[12] W. Shao, G. B. Guo, F. Y. Meng and Y. J. Gai: Efficient proposal distribution in Metropolis-Hastings algorithm using a B-splines technique. Manuscript. (2011).

[13] W. Shao, G. Q. Zhao and L. P. Zhu: Mixture normal proposal for Metropolis-Hastings algorithm. Manuscript. (2012).

[14] G. O. Robert, A. Gelman andW. R. Gilks: Weak convergence and optimal scaling of random walk Metropolis algorithm. The Annals of Applied Probability. 7: 110-120. (1997).

DOI: 10.1214/aoap/1034625254