• Journal of the Korean Data and Information Science Society
• /
• 제17권4호
• /
• pp.1387-1395
• /
• 2006

This paper considers testing for the ratio of two exponential means. We propose a solution based on a Bayesian decision rule to this problem in which no subjective input is considered. The criterion for testing is the Bayesian reference criterion (Bernardo, 1999). We derive the Bayesian reference criterion for testing the ratio of two exponential means. Simulation study and a real data example are provided.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.731-740
• /
• 2003

Schervish(1996) and Lavine and Schervish(1999) have shown that the classical P-values and the Bayes factors fail to achieve the so-called coherence property, respectively. In this paper, we propose a new type of Bayesian P-value, namely the type LR Bayesian P-value, satisfying the coherence property. The proposed Bayesian P-values are very easy to use with since they are simple functions of likelihood ratio. Their performances are discussed and compared with those of other methods under several situations.

• Journal of the Korean Data and Information Science Society
• /
• 제15권3호
• /
• pp.677-687
• /
• 2004

We consider the comparison of two one-parameter exponential distributions with the complete data as well as the type II censored data. We adapt Bayesian test procedure for nested hypothesis based on the Bayesian reference criterion. Specifically we derive the expression for the Bayesian reference criterion to solve our problem. Also we provide numerical examples using simulated data sets to illustrate our results.

• Communications for Statistical Applications and Methods
• /
• 제4권2호
• /
• pp.465-471
• /
• 1997

This paper deals with the problems of obtaining some Bayesian and empirical Bayesian Predictive densities and prediction intervals of a future observation $X_{(\tau+\gamma)}$ in the Rayleigh distribution. Using an inverse gamma prior distribution, some prodictive densities and prodiction intervals are proposed and studied. Also the behaviors of the proposed results are examined via numerical examples.

• Communications for Statistical Applications and Methods
• /
• 제4권1호
• /
• pp.185-191
• /
• 1997

Bayesian estimation of multinomial and Poisson parameters under starshped restriction is considered. Most Bayesian estimations in order restricted statistical inference require the high-dimensional integration which is very difficult to evaluate. Monte Carlo integration and Gibbs sampling are among alternative methods. The Bayesian estimation considered in this paper requires only evaluation of incomplete beta functions which are extensively tabulated.

• Communications for Statistical Applications and Methods
• /
• 제4권1호
• /
• pp.259-269
• /
• 1997

Bayesian inference for a record value statistics(RVS) model of nonhomogeneous Poisson process is considered. We seal with Bayesian inference for double exponential, Gamma, Rayleigh, Gumble RVS models using Gibbs sampling and Metropolis algorithm and also explore Bayesian computation and model selection.

• 한국방사선학회논문지
• /
• 제15권5호
• /
• pp.591-602
• /
• 2021

급성 허혈성 뇌졸중(Acute ischemic stroke; AIS) 환자는 증상발현 수 시간 이내 영상의학 검사를 통해 뇌경색(Infarction)을 조기 진단하여야 한다. 본 연구에서 SVD와 Bayesian 알고리즘을 이용한 뇌경색의 부피측정을 관류 전산화단층촬영(Computed tomography perfusion; CTP)과 확산 강조 자기공명영상(Magnetic resonance diffusion weighted image; MR DWI)을 비교하여 임상적 유용성을 알고자 하였다. 2017년 9월부터 2020년 9월까지 급성 허혈성 뇌졸중 증상으로 응급실을 내원한 환자 중 50명(남 : 여 = 33 : 17)의 영상의학 검사 정보를 후향적으로 이용하였다. SVD와 Bayesian 알고리즘으로 측정된 뇌경색 부피는 윌콕슨 부호순위검정(Wilcoxon signed rank test) 통계분석을 하여 중앙값(Median)과 사분위수(Iter quartile range; IQR) 25 - 75% 범위로 나타내었다. CTP 검사로 측정한 core volume(단위 : cc)은 SVD가 18.07 (7.76 - 33.98), Bayesian은 47.3 (23.76 - 79.11)으로 측정되었고 penumbra volume은 SVD가 140.24 (117.8 - 176.89), Bayesian은 105.05 (72.52 - 141.98)로 측정되었다. Mismatch ratio (%)는 SVD가 7.56 (4.36 - 15.26), Bayesian은 2.08 (1.68 - 2.77)로 측정되었으며 모든 측정값은 통계적으로 유의미한 차이가 있었다(p < 0.05). 스피어만 상관 분석(Spearman's correlation analysis) 결과는 CT Bayesian과 MR로 측정한 뇌경색 부피의 상관계수(r = 0.915)가 CT SVD와 MR의 상관계수(r = 0.763)보다 더욱 높은 양의 상관관계를 보였다(p < 0.01). 블랜드 알트만 산점도(Bland altman plot) 분석 결과는 CT Bayesian과 MR로 측정한 뇌경색 부피의 산점도 기울기(y = - 0.065)가 CT SVD와 MR의 산점도 기울기(y = - 0.749)보다 완만하게 측정되어 Bayesian이 더 높은 신뢰성을 나타내었다. 따라서 뇌경색 부피의 측정에서 Bayesian 알고리즘이 SVD보다 높은 정확도를 보였으므로 임상에서 유용하게 사용될 것으로 사료된다.

• 한국수자원학회논문집
• /
• 제41권1호
• /
• pp.35-47
• /
• 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 점 빈도분석을 수행하였으며, 특히 빈도분석에 있어서의 불확실성을 탐색하기 위하여 Bayesian 방법을 적용하고 그 결과를 기존에 사용되던 불확실성 탐색방법과 비교하였다. 본 논문의Ⅰ편에서는 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 여러 과정의 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 MCMC방법의 사전분포로 이용되었으며, 그 결과를 기존 불확실성의 추정방법의 하나인 2차 근사식을 이용한 최우추정(maximum likelihood estimation)방법의 결과와 비교하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.631-634
• /
• 2004

In this paper, the Bayesian recurrent neural network (BRNN) is proposed to predict time series data. Among the various traditional prediction methodologies, a neural network method is considered to be more effective in case of non-linear and non-stationary time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one need to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, we sets the weight vector as a state vector of state space method, and estimates its probability distributions in accordance with the Bayesian inference. This approach makes it possible to obtain more exact estimation of the weights. Moreover, in the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent network with Bayesian inference, what we call BRNN, is expected to show higher performance than the normal neural network. To verify the performance of the proposed method, the time series data are numerically generated and a neural network predictor is applied on it. As a result, BRNN is proved to show better prediction result than common feedforward Bayesian neural network.

• Smart Structures and Systems
• /
• 제15권2호
• /
• pp.395-408
• /
• 2015

This study aims to propose a Bayesian approach to consider changes in temperature and vehicle weight as environmental and operational factors for vibration-based long-term bridge health monitoring. The Bayesian approach consists of three steps: step 1 is to identify damage-sensitive features from coefficients of the auto-regressive model utilizing bridge accelerations; step 2 is to perform a regression analysis of the damage-sensitive features to consider environmental and operational changes by means of the Bayesian regression; and step 3 is to make a decision on the bridge health condition based on residuals, differences between the observed and predicted damage-sensitive features, utilizing 95% confidence interval and the Bayesian hypothesis testing. Feasibility of the proposed approach is examined utilizing monitoring data on an in-service bridge recorded over a one-year period. Observations through the study demonstrated that the Bayesian regression considering environmental and operational changes led to more accurate results than that without considering environmental and operational changes. The Bayesian hypothesis testing utilizing data from the healthy bridge, the damage probability of the bridge was judged as no damage.