论文信息 - Bayesian Multiple Change-point Estimation in Normal with EMC

Bayesian Multiple Change-point Estimation in Normal with EMC

In this paper, we estimate multiple change-points when the data follow the normal distributions in the Bayesian way. Evolutionary Monte Carlo (EMC) algorithm is applied into general Bayesian model with variable-dimension parameters and shows its usefulness and efficiency as a promising tool especially for computational issues. The method is applied to the humidity data of Seoul and the final model is determined based on BIC.

Sooyoung Cheon | Jaehee Kim | Sooyoung Cheon | Jaehee Kim

[1] H. Chernoff,et al. ESTIMATING THE CURRENT MEAN OF A NORMAL DISTRIBUTION WHICH IS SUBJECTED TO CHANGES IN TIME , 1964 .

[2] T. Fearn,et al. Multivariate Bayesian variable selection and prediction , 1998 .

[3] K. Hukushima,et al. Exchange Monte Carlo Method and Application to Spin Glass Simulations , 1995, cond-mat/9512035.

[4] P. Green. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[5] G. Parisi,et al. Simulated tempering: a new Monte Carlo scheme , 1992, hep-lat/9205018.

[6] L. Tierney. Markov Chains for Exploring Posterior Distributions , 1994 .

[7] Yi-Ching Yao. Estimation of a Noisy Discrete-Time Step Function: Bayes and Empirical Bayes Approaches , 1984 .

[8] Faming Liang,et al. Efficient MCMC estimation of discrete distributions , 2005, Comput. Stat. Data Anal..