• Journal of the Korean Statistical Society
• /
• v.26 no.4
• /
• pp.477-491
• /
• 1997

A new predictive classification rule for assigning future cases into one of two multivariate normal population (with unknown normal mixture model) is considered. The development involves calculation of posterior probability of each possible normal-mixture model via a default Bayesian test criterion, called intrinsic Bayes factor, and suggests predictive distribution for future cases to be classified that accounts for model uncertainty by weighting the effect of each model by its posterior probabiliy. In this paper, our interest is focused on constructing the classification rule that takes care of uncertainty about the types of covariance matrices (homogeneity/heterogeneity) involved in the model. For the constructed rule, a Monte Carlo simulation study demonstrates routine application and notes benefits over traditional predictive calssification rule by Geisser (1982).

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1455-1464
• /
• 2013

This paper develops maximum likelihood estimators (MLEs) of unknown parameters in an exponentiated half-logistic distribution based on a progressively type-II censored sample. We obtain approximate confidence intervals for the MLEs by using asymptotic variance and covariance matrices. Using importance sampling, we obtain Bayes estimators and corresponding credible intervals with the highest posterior density and Bayes predictive intervals for unknown parameters based on progressively type-II censored data from an exponentiated half logistic distribution. For illustration purposes, we examine the validity of the proposed estimation method by using real and simulated data.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.10a
• /
• pp.24-30
• /
• 1993

When modeling a complex system we use an event tree to analyze propagation of failure. An event tree cannot represent the statistical interrelationships among parameters, but it can be represented as a statistically identical influence diagram so that parameter updating can be easily performed. After updating parameters we can calculate posterior distribution of the failure rate for each path. But exact distribution requires considerably complex numerical integration. We propose an approximation method to calculate the posterior and derive the predictive distribution of the time to next failure. Finally we introduce the system which implements our methodology.

• Journal of the Korean Statistical Society
• /
• v.30 no.2
• /
• pp.179-192
• /
• 2001

When a statistical model has a hierarchical structure such as multilayer perceptrons in neural networks or Gaussian mixture density representation, the model includes distribution with unidentifiable parameters when the structure becomes redundant. Since the exact structure is unknown, we need to carry out statistical estimation or learning of parameters in such a model. From the geometrical point of view, distributions specified by unidentifiable parameters become a singular point in the parameter space. The problem has been remarked in many statistical models, and strange behaviors of the likelihood ratio statistics, when the null hypothesis is at a singular point, have been analyzed so far. The present paper studies asymptotic behaviors of the maximum likelihood estimator and the Bayesian predictive estimator, by using a simple cone model, and show that they are completely different from regular statistical models where the Cramer-Rao paradigm holds. At singularities, the Fisher information metric degenerates, implying that the cramer-Rao paradigm does no more hold, and that he classical model selection theory such as AIC and MDL cannot be applied. This paper is a first step to establish a new theory for analyzing the accuracy of estimation or learning at around singularities.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.3
• /
• pp.193-199
• /
• 2000

In many studies, considerable attention has been focussed upon choosing a model which represents underlying process of time series and forecasting the future. In the real world, however, there may be some cases that one model can not reflect all the characteristics of original time series. Under such circumstances, we may get better performance by combining the forecasts from several models. The most popular methods for combining forecasts involve taking a weighted average of multiple forecasts. But the weights are usually unstable. In cases the assumptions of normality and unbiasedness for forecast errors are satisfied, a Bayesian method can be used for updating the weights. In the real world, however, there are many circumstances the Bayesian method is not appropriate. This paper proposes a PNN(Probabilistic Neural Net) approach as a method for combining forecasts that can be applied when the assumption of normality or unbiasedness for forecast errors is not satisfied. In this paper, PNN method, which is similar to Bayesian approach, is suggested as an updating method of the unstable weights in the combination of the forecasts. The PNN method has been usually used in the field of pattern recognition. Unlike the Bayesian approach, it requires no assumption of a specific prior distribution because it gets probabilities by using the distribution estimated from given data. Empirical results reveal that the PNN method offers superior predictive capabilities.

• The Korean Journal of Applied Statistics
• /
• v.21 no.5
• /
• pp.835-843
• /
• 2008

In this paper, we investigate a Bayesian inference for software reliability models based on mean value functions which take the form of the mixture of beta distribution functions. The posterior simulation via the Markov chain Monte Carlo approach is used to produce estimates of posterior properties. Its applicability is illustrated with two real data sets. We compute the predictive distribution and the marginal likelihood of various models to compare the performance of them. The model comparison results show that the model based on the beta-mixture performs better than other models.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.4
• /
• pp.393-400
• /
• 2011

In this study, a procedure for the inverse estimation of the fatigue life parameters of springs which utilize the field fatigue life test data is proposed to replace real test with the FEA on fatigue life prediction. The Bayesian approach is employed, in which the posterior distributions of the parameters are determined conditional on the accumulated life data that are routinely obtained from the regular tests. In order to obtain the accurate samples from the distributions, the Markov chain Monte Carlo (MCMC) technique is employed. The distributions of the parameters are used in the FEA for predicting the fatigue life in the form of a predictive interval. The results show that the actual fatigue life data are found well within the posterior predictive distributions.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.77-86
• /
• 2021

A method of constructing a war simulation based on Bayesian Inference was proposed as a method of constructing heterogeneous historical war data obtained with a time difference into a single model. A method of applying a linear regression model can be considered as a method of predicting future battles by analyzing historical war results. However it is not appropriate for two heterogeneous types of historical data that reflect changes in the battlefield environment due to different times to be suitable as a single linear regression model and violation of the model's assumptions. To resolve these problems a Bayesian inference method was proposed to obtain a post-distribution by assuming the data from the previous era as a non-informative prior distribution and to infer the final posterior distribution by using it as a prior distribution to analyze the data obtained from the next era. Another advantage of the Bayesian inference method is that the results sampled by the Markov Chain Monte Carlo method can be used to infer posterior distribution or posterior predictive distribution reflecting uncertainty. In this way, it has the advantage of not only being able to utilize a variety of information rather than analyzing it with a classical linear regression model, but also continuing to update the model by reflecting additional data obtained in the future.

• Journal of the Korean Statistical Society
• /
• v.25 no.4
• /
• pp.577-588
• /
• 1996

The Bayes factor provides a possible hierarchical Bayesian approach for studying the change point problems. A hypothesis for testing change versus no change is considered using predictive distributions. When the underlying distribution is in one-parameter exponential family with conjugate priors, Bayes factors are investigated to the hypothesis above. Finally one example is provided .

• Journal of Korea Water Resources Association
• /
• v.53 no.7
• /
• pp.481-491
• /
• 2020

The development of agricultural land at Saemangeum has required a significant increase in agricultural water use. It has been well acknowledged that salinity plays a critical role in the farming system. Therefore, a systematic study in salinity is necessary to better manage agricultural water. This study aims to develop a stochastic salinity simulation model that simultaneously simulates salinities obtained from different layers. More specifically, this study proposed a two-stage Autoregressive Exgeneous (ARX) model within a hierarchical Bayesian modeling framework. We derived posterior distributions of model parameters and further used them to obtain the predictive posterior distribution for salinities at three different layers. Here, the BIC values are used and compared to determine the optimal model from a set of candidate models. A detailed discussion of the model is provided.