• Title/Summary/Keyword: Metropolis-Hastings

Search Result 51, Processing Time 0.022 seconds

Uncertainty Analysis for Parameters of Probability Distribution in Rainfall Frequency Analysis: Bayesian MCMC and Metropolis-Hastings Algorithm (강우빈도분석에서 확률분포의 매개변수에 대한 불확실성 해석: Bayesian MCMC 및 Metropolis-Hastings 알고리즘을 중심으로)

  • Seo, Young-Min;Jee, Hong-Kee;Lee, Soon-Tak
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2010.05a
    • /
    • pp.1385-1389
    • /
    • 2010
  • 수자원 계획에 있어서 강우 또는 홍수빈도분석시 주로 사용되는 확률의 개념은 상대빈도에 대한 극한으로 확률을 정의하는 빈도학파적 확률관점에 속하며, 확률모델에서 미지의 매개변수들은 고정된 상수로 간주된다. 따라서 확률은 객관적이고 매개변수들은 고정된 값을 가지기 때문에 이러한 매개변수들에 대한 확률론적 설명은 매우 어렵다. 본 연구에서는 강우빈도해석에서 확률분포의 매개변수에 대한 불확실성을 정량화하기 위하여 베이지안 MCMC 및 Metropolis-Hastings 알고리즘을 이용한 불확실성 평가모델을 구축하였다. 그리고 베이지안 MCMC 및 Metropolis-Hastings 알고리즘의 적용을 통하여 확률강우량 산정시 확률분포의 매개변수에 대한 통계학적 특성 및 불확실성 구간을 정량화하였으며, 이를 바탕으로 홍수위험평가 및 의사결정과정에서 불확실성 및 위험도를 충분히 설명할 수 있는 프레임워크 구성을 위한 기초를 마련할 수 있었다.

  • PDF

Uncertainty Analysis for Parameters of Probability Distribution in Rainfall Frequency Analysis by Bayesian MCMC and Metropolis Hastings Algorithm (Bayesian MCMC 및 Metropolis Hastings 알고리즘을 이용한 강우빈도분석에서 확률분포의 매개변수에 대한 불확실성 해석)

  • Seo, Young-Min;Park, Ki-Bum
    • Journal of Environmental Science International
    • /
    • v.20 no.3
    • /
    • pp.329-340
    • /
    • 2011
  • The probability concepts mainly used for rainfall or flood frequency analysis in water resources planning are the frequentist viewpoint that defines the probability as the limit of relative frequency, and the unknown parameters in probability model are considered as fixed constant numbers. Thus the probability is objective and the parameters have fixed values so that it is very difficult to specify probabilistically the uncertianty of these parameters. This study constructs the uncertainty evaluation model using Bayesian MCMC and Metropolis -Hastings algorithm for the uncertainty quantification of parameters of probability distribution in rainfall frequency analysis, and then from the application of Bayesian MCMC and Metropolis- Hastings algorithm, the statistical properties and uncertainty intervals of parameters of probability distribution can be quantified in the estimation of probability rainfall so that the basis for the framework configuration can be provided that can specify the uncertainty and risk in flood risk assessment and decision-making process.

Metropolis-Hastings Expectation Maximization Algorithm for Incomplete Data (불완전 자료에 대한 Metropolis-Hastings Expectation Maximization 알고리즘 연구)

  • Cheon, Soo-Young;Lee, Hee-Chan
    • The Korean Journal of Applied Statistics
    • /
    • v.25 no.1
    • /
    • pp.183-196
    • /
    • 2012
  • The inference for incomplete data such as missing data, truncated distribution and censored data is a phenomenon that occurs frequently in statistics. To solve this problem, Expectation Maximization(EM), Monte Carlo Expectation Maximization(MCEM) and Stochastic Expectation Maximization(SEM) algorithm have been used for a long time; however, they generally assume known distributions. In this paper, we propose the Metropolis-Hastings Expectation Maximization(MHEM) algorithm for unknown distributions. The performance of our proposed algorithm has been investigated on simulated and real dataset, KOSPI 200.

Hierarchical Bayesian Inference of Binomial Data with Nonresponse

  • Han, Geunshik;Nandram, Balgobin
    • Journal of the Korean Statistical Society
    • /
    • v.31 no.1
    • /
    • pp.45-61
    • /
    • 2002
  • We consider the problem of estimating binomial proportions in the presence of nonignorable nonresponse using the Bayesian selection approach. Inference is sampling based and Markov chain Monte Carlo (MCMC) methods are used to perform the computations. We apply our method to study doctor visits data from the Korean National Family Income and Expenditure Survey (NFIES). The ignorable and nonignorable models are compared to Stasny's method (1991) by measuring the variability from the Metropolis-Hastings (MH) sampler. The results show that both models work very well.

At-site Low Flow Frequency Analysis Using Bayesian MCMC: I. Comparative study for construction of Prior distribution (Bayesian MCMC를 이용한 저수량 점 빈도분석: I. 사전분포의 적용성 비교)

  • Kim, Sang-Ug;Lee, Kil-Seong;Park, Kyung-Shin
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2008.05a
    • /
    • pp.1121-1124
    • /
    • 2008
  • 저수분석(low flow analysis)은 수자원공학에서 중요한 분야 중 하나이며, 특히 저수량 빈도분석(low flow frequency analysis)의 결과는 저수(貯水)용량의 설계, 물 수급계획, 오염원의 배치 및 관개와 생태계의 보존을 위한 수량과 수질의 관리에 중요하게 사용된다. 그러므로 본 연구에서는 저수량 빈도분석을 위한 점빈도분석을 수행하였으며, 특히 빈도분석에 있어서의 불확실성을 탐색하기 위하여 Bayesian 방법을 적용하고 그 결과를 기존에 사용되던 불확실성 탐색방법과 비교하였다. 본 논문의 I편에서는 Bayesian 방법 중 사전분포(prior distribution)와 우도함수(likelihood function)의 복잡성에 상관없이 계산이 가능한 Bayesian MCMC(Bayesian Markov Chain Monte Carlo) 방법과 Metropolis-Hastings 알고리즘을 사용하기 위한 여러과정의 이론적 배경과 Bayesian 방법에서 가장 중요한 요소인 사전분포를 구축하고 이를 비교 및 평가하였다. 고려된 사전분포는 자료에 기반하지 않은 사전분포와 자료에 기반한 사전분포로써 두 사전분포를 이용하여 Metropolis-Hastings 알고리즘을 수행하고 그 결과를 비교하여 저수량 빈도분석에 합리적인 사전분포를 선정하였다. 또한 알고리즘의 수행과정에서 필요한 제안분포(proposal distribution)를 적용하여 그에 따른 알고리즘의 효율성을 채택률(acceptance rate)을 산정하여 검증해 보았다. 사전분포의 분석 결과, 자료에 기반한 사전분포가 자료에 기반하지 않은 사전분포보다 정확성 및 불확실성의 표현에 있어서 우수한 결과를 제시하는 것을 확인할 수 있었고, 채택률을 이용한 알고리즘의 효용성 역시 기존 연구자들이 제시하였던 만족스러운 범위를 가지는 것을 알 수 있었다. 최종적으로 선정된 사전분포는 본 연구의 II편에서 Bayesian MCMC 방법의 사전분포로 이용되었으며, 그 결과를 기존 불확실성의 추정방법의 하나인 2차 근사식을 이용한 최우추정(maximum likelihood estimation)방법의 결과와 비교하였다.

  • PDF

Bayesian Multiple Change-Point for Small Data (소량자료를 위한 베이지안 다중 변환점 모형)

  • Cheon, Soo-Young;Yu, Wenxing
    • Communications for Statistical Applications and Methods
    • /
    • v.19 no.2
    • /
    • pp.237-246
    • /
    • 2012
  • Bayesian methods have been recently used to identify multiple change-points. However, the studies for small data are limited. This paper suggests the Bayesian noncentral t distribution change-point model for small data, and applies the Metropolis-Hastings-within-Gibbs Sampling algorithm to the proposed model. Numerical results of simulation and real data show the performance of the new model in terms of the quality of the resulting estimation of the numbers and positions of change-points for small data.

At-site Low Flow Frequency Analysis Using Bayesian MCMC: I. Theoretical Background and Construction of Prior Distribution (Bayesian MCMC를 이용한 저수량 점 빈도분석: I. 이론적 배경과 사전분포의 구축)

  • Kim, Sang-Ug;Lee, Kil-Seong
    • Journal of Korea Water Resources Association
    • /
    • v.41 no.1
    • /
    • pp.35-47
    • /
    • 2008
  • The low flow analysis is an important part in water resources engineering. Also, the results of low flow frequency analysis can be used for design of reservoir storage, water supply planning and design, waste-load allocation, and maintenance of quantity and quality of water for irrigation and wild life conservation. Especially, for identification of the uncertainty in frequency analysis, the Bayesian approach is applied and compared with conventional methodologies in at-site low flow frequency analysis. In the first manuscript, the theoretical background for the Bayesian MCMC (Bayesian Markov Chain Monte Carlo) method and Metropolis-Hasting algorithm are studied. Two types of the prior distribution, a non-data- based and a data-based prior distributions are developed and compared to perform the Bayesian MCMC method. It can be suggested that the results of a data-based prior distribution is more effective than those of a non-data-based prior distribution. The acceptance rate of the algorithm is computed to assess the effectiveness of the developed algorithm. In the second manuscript, the Bayesian MCMC method using a data-based prior distribution and MLE(Maximum Likelihood Estimation) using a quadratic approximation are performed for the at-site low flow frequency analysis.

On the Bayesian Statistical Inference (베이지안 통계 추론)

  • Lee, Ho-Suk
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2007.06c
    • /
    • pp.263-266
    • /
    • 2007
  • This paper discusses the Bayesian statistical inference. This paper discusses the Bayesian inference, MCMC (Markov Chain Monte Carlo) integration, MCMC method, Metropolis-Hastings algorithm, Gibbs sampling, Maximum likelihood estimation, Expectation Maximization algorithm, missing data processing, and BMA (Bayesian Model Averaging). The Bayesian statistical inference is used to process a large amount of data in the areas of biology, medicine, bioengineering, science and engineering, and general data analysis and processing, and provides the important method to draw the optimal inference result. Lastly, this paper discusses the method of principal component analysis. The PCA method is also used for data analysis and inference.

  • PDF

DEFAULT BAYESIAN INFERENCE OF REGRESSION MODELS WITH ARMA ERRORS UNDER EXACT FULL LIKELIHOODS

  • Son, Young-Sook
    • Journal of the Korean Statistical Society
    • /
    • v.33 no.2
    • /
    • pp.169-189
    • /
    • 2004
  • Under the assumption of default priors, such as noninformative priors, Bayesian model determination and parameter estimation of regression models with stationary and invertible ARMA errors are developed under exact full likelihoods. The default Bayes factors, the fractional Bayes factor (FBF) of O'Hagan (1995) and the arithmetic intrinsic Bayes factors (AIBF) of Berger and Pericchi (1996a), are used as tools for the selection of the Bayesian model. Bayesian estimates are obtained by running the Metropolis-Hastings subchain in the Gibbs sampler. Finally, the results of numerical studies, designed to check the performance of the theoretical results discussed here, are presented.

Bayesian Parameter Estimation using the MCMC method for the Mean Change Model of Multivariate Normal Random Variates

  • Oh, Mi-Ra;Kim, Eoi-Lyoung;Sim, Jung-Wook;Son, Young-Sook
    • Communications for Statistical Applications and Methods
    • /
    • v.11 no.1
    • /
    • pp.79-91
    • /
    • 2004
  • In this thesis, Bayesian parameter estimation procedure is discussed for the mean change model of multivariate normal random variates under the assumption of noninformative priors for all the parameters. Parameters are estimated by Gibbs sampling method. In Gibbs sampler, the change point parameter is generated by Metropolis-Hastings algorithm. We apply our methodology to numerical data to examine it.