• Journal of Korea Water Resources Association
• /
• v.46 no.1
• /
• pp.13-24
• /
• 2013

The main objective of this study was to develop a new regional frequency analysis model based on hierarchical Bayesian model that allows us to better estimate and quantify model parameters as well as their associated uncertainties. A Monte-carlo experiment procedure has been set up to verify the proposed regional frequency analysis. It was found that the proposed hierarchical Bayesian model based regional frequency analysis outperformed the existing L-moment based regional frequency analysis in terms of reducing biases associated with the model parameters. Especially, the bias is remarkably decreased with increasing return period. The proposed model was applied to six weather stations in Jeollabuk-do, and compared with the existing L-moment approach. This study also provided shrinkage process of the model parameters that is a typical behavior in hierarchical Bayes models. The results of case study show that the proposed model has the potential to obtain reliable estimates of the parameters and quantitatively provide their uncertainties.

• Journal of the Korean Statistical Society
• /
• v.36 no.1
• /
• pp.129-148
• /
• 2007

Frailty estimates from the proportional hazards frailty model often lead us to conjecture the heterogeneity in frailty such that the variance of the frailty varies over different covariate groups (e.g. male group versus female group). For such systematic heterogeneity in frailty, we consider a regression model for the variance components in the proportional hazards frailty model, denoted by the MLFM. However, in many cases, the observed data do not show any statistically significant preference between the homogeneous frailty model and the heterogeneous frailty model. In this paper, we propose a Bayesian model averaging procedure with the reversible jump Markov chain Monte Carlo which selects the appropriate model automatically. The resulting regression coefficient estimate ignores the model uncertainty from the frailty distribution in view of Bayesian model averaging (Hoeting et al., 1999). Finally, the proposed model and the estimation procedure are illustrated through the analysis of the kidney infection data in McGilchrist and Aisbett (1991) and a simulation study is implemented.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.1
• /
• pp.9-18
• /
• 2016

In the Heckman-Meyers model, which is frequently referred by IAA, Swiss Solvency Test, EU Solvency II, the assumption of parameter distribution is key factor. While in theory Bayesian analysis somewhat reflects parameter uncertainty using prior distribution, it is often the case where both Heckman-Meyers and Bayesian are necessary to better manage the parameter uncertainty. Therefore, this paper proposes the use of Bayesian H-M CRM, a combination of Heckman-Meyers model and Bayesian, and analyzes its efficiency.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.4
• /
• pp.259-275
• /
• 2021

This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.

• Communications for Statistical Applications and Methods
• /
• v.25 no.2
• /
• pp.131-157
• /
• 2018

We propose a robust event date model to estimate the date of a target event by a combination of individual dates obtained from archaeological artifacts assumed to be contemporaneous. These dates are affected by errors of different types: laboratory and calibration curve errors, irreducible errors related to contaminations, and taphonomic disturbances, hence the possible presence of outliers. Modeling based on a hierarchical Bayesian statistical approach provides a simple way to automatically penalize outlying data without having to remove them from the dataset. Prior information on individual irreducible errors is introduced using a uniform shrinkage density with minimal assumptions about Bayesian parameters. We show that the event date model is more robust than models implemented in BCal or OxCal, although it generally yields less precise credibility intervals. The model is extended in the case of stratigraphic sequences that involve several events with temporal order constraints (relative dating), or with duration, hiatus constraints. Calculations are based on Markov chain Monte Carlo (MCMC) numerical techniques and can be performed using ChronoModel software which is freeware, open source and cross-platform. Features of the software are presented in Vibet et al. (ChronoModel v1.5 user's manual, 2016). We finally compare our prior on event dates implemented in the ChronoModel with the prior in BCal and OxCal which involves supplementary parameters defined as boundaries to phases or sequences.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.273-278
• /
• 2014

In vocabulary recognition using HMM(Hidden Markov Model) by model for the observation of a discrete probability distribution indicates the advantages of low computational complexity, but relatively low recognition rate. Improve them with a HMM model is proposed for the optimization of the Bayesian methods. In this paper is posterior distribution and prior distribution in recognition Gaussian mixtures model provides a model to optimize of the Bayesian methods vocabulary recognition. The result of applying the proposed method, the recognition rate of 97.9% in vocabulary recognition, respectively.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.2941-2959
• /
• 2022

The fire brigade non-suppression probability model is a major factor that should be considered in evaluating fire-induced risk through fire probabilistic risk assessment (PRA), and also uncertainty is a critical consideration in support of risk-informed performance-based (RIPB) fire protection decision-making. This study developed an optimal integrated probabilistic fire brigade non-suppression model considering uncertainty of parameters based on the Bayesian Markov Chain Monte Carlo (MCMC) approach on electrical fire which is one of the most risk significant contributors. The result shows that the log-normal probability model with a location parameter (µ) of 2.063 and a scale parameter (σ) of 1.879 is best fitting to the actual fire experience data. It gives optimal model adequacy performance with Bayesian information criterion (BIC) of -1601.766, residual sum of squares (RSS) of 2.51E-04, and mean squared error (MSE) of 2.08E-06. This optimal log-normal model shows the better performance of the model adequacy than the exponential probability model suggested in the current fire PRA methodology, with a decrease of 17.3% in BIC, 85.3% in RSS, and 85.3% in MSE. The outcomes of this study are expected to contribute to the improvement and securement of fire PRA realism in the support of decision-making for RIPB fire protection programs.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.53 no.6
• /
• pp.925-933
• /
• 2020

This study is aimed to compare stock assessment models which are effective in assessing red snow crab Chinonoecetes japonicus resources and to select and apply an effective stock assessment model in the future. In order to select an effective stock assessment model, a process-error model, observation-error model, and a Bayesian state-space model were estimated. Analytical results show that the least error is observed between the estimated CPUE (catch per unit effort) and the observed CPUE when using the Bayesian state-space model. For the Bayesian state-space model, the 95% credible interval(CI) ranges for the maximum sustainable yield (MSY), carrying capacity (K), catchability coefficient (q), and intrinsic growth (r) are estimated to be 10,420-47,200 tons, 185,200-444,800 tons, 3.81E-06-9.02E-06, and 0.14-0.66, respectively. The results show that the Bayesian state-space model was most reliable among models.

• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.737-746
• /
• 2013

The Bayesian method can be applied successfully to the estimation of the censored regression model introduced by Tobin (1958). The Bayes estimates show improvements over the maximum likelihood estimate; however, the performance of the Bayesian interval estimation is questionable. In Bayesian paradigm, the prior distribution usually reflects personal beliefs about the parameters. Such subjective priors will typically yield interval estimators with poor frequentist properties; however, an objective noninformative often yields a Bayesian procedure with good frequentist properties. We examine the performance of frequentist properties of noninformative priors for the Tobit regression model.

• The Korean Journal of Applied Statistics
• /
• v.36 no.4
• /
• pp.349-360
• /
• 2023

Dynamic Nelson-Siegel model is widely used in modeling term structure of interest rates for financial products. In this study, we explain dynamic Nelson-Siegel model from the perspective of the state space model and explore Bayesian approaches that can be applied to that model. By applying SOFR term rate data to the Bayesian dynamic Nelson-Siegel model, we confirm the performance and compare it with other competing models such as Vasicek model, dynamic Nelson-Siegel model based on the frequentist approach, and the two-factor Bayesian dynamic Nelson-Siegel model. We also confirm that the Bayesian dynamic Nelson-Siegel model outperformed its competitors on SOFR term rate data based on RMSE.