• Journal of Radiation Protection and Research
• /
• v.41 no.2
• /
• pp.149-154
• /
• 2016

Background: Any real application of Bayesian inference must acknowledge that both prior distribution and likelihood function have only been specified as more or less convenient approximations to whatever the analyzer's true belief might be. If the inferences from the Bayesian analysis are to be trusted, it is important to determine that they are robust to such variations of prior and likelihood as might also be consistent with the analyzer's stated beliefs. Materials and Methods: The robust Bayesian inference was applied to atmospheric dispersion assessment using Gaussian plume model. The scopes of contaminations were specified as the uncertainties of distribution type and parametric variability. The probabilistic distribution of model parameters was assumed to be contaminated as the symmetric unimodal and unimodal distributions. The distribution of the sector-averaged relative concentrations was then calculated by applying the contaminated priors to the model parameters. Results and Discussion: The sector-averaged concentrations for stability class were compared by applying the symmetric unimodal and unimodal priors, respectively, as the contaminated one based on the class of ${\varepsilon}$-contamination. Though ${\varepsilon}$ was assumed as 10%, the medians reflecting the symmetric unimodal priors were nearly approximated within 10% compared with ones reflecting the plausible ones. However, the medians reflecting the unimodal priors were approximated within 20% for a few downwind distances compared with ones reflecting the plausible ones. Conclusion: The robustness has been answered by estimating how the results of the Bayesian inferences are robust to reasonable variations of the plausible priors. From these robust inferences, it is reasonable to apply the symmetric unimodal priors for analyzing the robustness of the Bayesian inferences.

• Journal of the Korean Statistical Society
• /
• v.28 no.3
• /
• pp.311-324
• /
• 1999

The problem of 'outliers', observations which look suspicious in some way, has long been one of the most concern in the statistical structure to experimenters and data analysts. We propose a model for an outlier problem and also analyze it in linear regression model using a Bayesian approach. Then we use the mean-shift model and SSVS(George and McCulloch, 1993)'s idea which is based on the data augmentation method. The advantage of proposed method is to find a subset of data which is most suspicious in the given model by the posterior probability. The MCMC method(Gibbs sampler) can be used to overcome the complicated Bayesian computation. Finally, a proposed method is applied to a simulated data and a real data.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.805-814
• /
• 2001

The problem of 'outliers', observations which look suspicious in some way, has long been one of the most concern in the statistical structure to experimenters and data analysts. We propose a model for outliers problem and also analyze it in linear regression model using a Bayesian approach with the variance-inflation model. We will use Geweke's(1996) ideas which is based on the data augmentation method for detecting outliers in linear regression model. The advantage of the proposed method is to find a subset of data which is most suspicious in the given model by the posterior probability The sampling based approach can be used to allow the complicated Bayesian computation. Finally, our proposed methodology is applied to a simulated and a real data.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.877-885
• /
• 2006

Recently it is proposed that the Bayesian networks used as conversational agent for topic inference is useful but the Bayesian networks require much time to model, and the Bayesian networks also have to be modified when the scripts, the database for conversation, are added or modified and this hinders the scalability of the agent. This paper presents a method to improve the scalability of the agent by constructing the Bayesian network from scripts automatically. The proposed method is to model the structure of Bayesian networks hierarchically and to utilize Noisy-OR gate to form the conditional probability distribution table (CPT). Experimental results with ten subjects confirm the usefulness of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.39-48
• /
• 2005

This paper proposes novel texture segmentation method using Bayesian estimation method and neural networks. We use multi-scale wavelet coefficients and the context information of neighboring wavelets coefficients as the input of networks. The output of neural networks is modeled as a posterior probability. The context information is obtained by HMT(Hidden Markov Tree) model. This proposed segmentation method shows better performance than ML(Maximum Likelihood) segmentation using HMT model. And post-processed texture segmentation results as using multi-scale Bayesian image segmentation technique called HMTseg in each segmentation by HMT and the proposed method also show that the proposed method is superior to the method using HMT.

• Journal of Korea Water Resources Association
• /
• v.49 no.6
• /
• pp.481-493
• /
• 2016

The statistical analysis to the torrential rainfall data that is defined as a rainfall amount more than 80 mm/day is performed with Daegu and Busan rainfall data which is collected during 384 months. The number of occurrence of the torrential rainfall events can be simulated usually using Poisson distribution. However, the Poisson distribution can be frequently failed to simulate the statistical characteristics of the observed value when the observed data is zero-inflated. Therefore, in this study, Generalized Poisson distribution (GPD), Zero-Inflated Poisson distribution (ZIP), Zero-Inflated Generalized Poisson distribution (ZIGP), and Bayesian ZIGP model were used to resolve the zero-inflated problem in the torrential rainfall data. Especially, in Bayesian ZIGP model, a informative prior distribution was used to increase the accuracy of that model. Finally, it was suggested that POI and GPD model should be discouraged to fit the frequency of the torrential rainfall data. Also, Bayesian ZIGP model using informative prior provided the most accurate results. Additionally, it was recommended that ZIP model could be alternative choice on the practical aspect since the Bayesian approach of this study was considerably complex.

• Journal of Environmental Science International
• /
• v.27 no.7
• /
• pp.499-507
• /
• 2018

Agricultural meteorological information is an important resource that affects farmers' income, food security, and agricultural conditions. Thus, such data are used in various fields that are responsible for planning, enforcing, and evaluating agricultural policies. The meteorological information obtained from automatic weather observation systems operated by rural development agencies contains missing values owing to temporary mechanical or communication deficiencies. It is known that missing values lead to reduction in the reliability and validity of the model. In this study, the hierarchical Bayesian spatio-temporal model suggests replacements for missing values because the meteorological information includes spatio-temporal correlation. The prior distribution is very important in the Bayesian approach. However, we found a problem where the spatial decay parameter was not converged through the trace plot. A suitable spatial decay parameter, estimated on the bias of root-mean-square error (RMSE), which was determined to be the difference between the predicted and observed values. The latitude, longitude, and altitude were considered as covariates. The estimated spatial decay parameters were 0.041 and 0.039, for the spatio-temporal model with latitude and longitude and for latitude, longitude, and altitude, respectively. The posterior distributions were stable after the spatial decay parameter was fixed. root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and bias were calculated for model validation. Finally, the missing values were generated using the independent Gaussian process model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.280-280
• /
• 2016

특정 자료의 시간의 흐름에 따른 예측치를 추정하는 방법으로 AR Model 즉, 자기회귀모형이 많이 사용되고 있다. AR Model은 변수의 현재 값을 과거 값의 함수로 나타내게 되는데, 이런 시계열 분석 모델을 사용할 때 매개변수의 추정 과정이 필수적으로 요구된다. 일반적으로 매개변수를 추정하는 방법에는 확률적근사법(stochastic approximation), 최소제곱법(method of least square), 자기상관법(method of autocorrelation method), 최우도법(method of maximum likelihood) 등이 있다. AR Model에서 가장 많이 사용되는 최우도법은 표본크기가 충분히 클 때 가장 효율적인 방법으로 평가되지만 수치적으로 해를 구하는 과정이 복잡한 경우가 많으며, 해를 구하지 못하는 어려움이 따르기도 한다. 또한 표본 크기가 작을 때 일반적으로 잘 일치하지 않은 결과를 얻게 된다. 우리나라의 강우, 유량 등의 자료는 자료의 수가 적은 경우가 많기 때문에 최우도법을 통한 매개변수 추정 시 불확실성이 내재되어있지만 그것을 정량적으로 제시하는데 한계가 있다. 본 연구에서는 AR Model의 매개변수 추정 시 Bayesian 기법으로 매개변수의 사후분포(posterior distribution)를 제공하여 매개변수의 불확실성 구간을 정량적으로 표현하게 됨으로써, 시계열 분석을 통해 보다 신뢰성 있는 예측치를 얻을 수 있으리라 판단된다.

• Journal of Applied Reliability
• /
• v.13 no.4
• /
• pp.229-239
• /
• 2013

This paper reports a manner to use a Bayesian approach to derive the optimal replacement policy. In order to produce a system with minimal repair warranty, a replacement model with the extended warranty is considered. Within the warranty period, the failed system is minimally repaired by the manufacturer at no cost to the end-user. The failure time is assumed to follow a Weibull distribution with unknown parameters. The expected cost rate per unit time, from the end-user's viewpoints, is induced by the Bayesian approach, and the optimal replacement policy to minimize the cost rate is proposed. Finally, a numerical example illustrating to derive the optimal replacement policy based on the Bayesian approach is described.

• The Korean Journal of Applied Statistics
• /
• v.7 no.2
• /
• pp.9-19
• /
• 1994

Beta-binomial model, which is reparametrized in terms of the mean probability $\mu$ of a positive deagnosis and the $\kappa$ of agreement, is widely used in psychology. When $\mu$ is close to 0, inference about $\kappa$ become difficult because likelihood function becomes constant. We consider Bayesian approach in this case. To apply Bayesian analysis, Gibbs sampler is used to overcome difficulties in integration. Marginal posterior density functions are estimated and Bayesian estimates are derived by using Gibbs sampler and compare the results with the one obtained by using numerical integration.