• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.630-642
• /
• 2015

In Jøsang's subjective logic, the fusion operator is not able to fuse three or more opinions at a time and it cannot consider the effect of time factors on fusion. Also, the base rate (a) and non-informative prior weight (C) could not change dynamically. In this paper, we propose an Improved Subjective Logic Model with Evidence Driven (ISLM-ED) that expands and enriches the subjective logic theory. It includes the multi-agent unified fusion operator and the dynamic function for the base rate (a) and the non-informative prior weight (C) through the changes in evidence. The multi-agent unified fusion operator not only meets the commutative and associative law but is also consistent with the researchers's cognitive rules. A strict mathematical proof was given by this paper. Finally, through the simulation experiments, the results show that the ISLM-ED is more reasonable and effective and that it can be better adapted to the changing environment.

• Journal of the Korean Statistical Society
• /
• 제34권4호
• /
• pp.331-344
• /
• 2005

Inference on current data could be more reliable if there exist similar data based on previous studies. Ibrahim and Chen (2000) utilize these data to characterize the power prior. The power prior is constructed by raising the likelihood function of the historical data to the power $a_o$, where $0\;{\le}\;a_o\;{\le}\;1$. The power prior is a useful informative prior in Bayesian inference. However, for model selection or model comparison problems, the propriety of the power prior is one of the critical issues. In this paper, we suggest two joint power priors for the power law process and show that they are proper under some conditions. We demonstrate our results with a real dataset and some simulated datasets.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.719-729
• /
• 2003

We propose a Bayesian model selection procedure for nonlinear regression models under noninformative prior. For informative prior, Na and Kim (2002) suggested the Bayesian model selection procedure through MCMC techniques. We extend this method to the case of noninformative prior. The difficulty with the use of noninformative prior is that it is typically improper and hence is defined only up to arbitrary constant. The methods, such as Intrinsic Bayes Factor(IBF) and Fractional Bayes Factor(FBF), are used as a resolution to the problem. We showed the detailed model selection procedure through the specific real data set.

• 응용통계연구
• /
• 제14권1호
• /
• pp.161-175
• /
• 2001

메타분석(Meta-analysis)은 서로 독립적으로 연구되어진 결과들을 전체적인 하나의 결과로 도출하기 위해 사용되어지는 통계적 방법이다. 이러한 통계적 방법을 설명할 모형으로는 선택모형(selection model)을 포함한 계층적 모형(hierarchical model)을 사용하며, 이러한 모형들은 베이지안 메타분석에 유용한 것으로 알려져 있다. 그러나, 메타분석의 자료들은 일반적으로 출판편의(publication bias)를 갖고 있으므로 이를 극복하고자 가중함수(weight function)를 이용하여 분포함수를 새롭게 정의하여 사용한다. 최근에 Silliman(1997)은 계층적 모형(hierarchical model)에 가중함수를 첨부한 계층적 선택모형(hierarchical selection model)을 정의하고 모수적 베이지안 방법을 제시하였다. 본 연구에서는 미관측된 연구효과에 디리슈레 과정 사전분포(Dirichlet process prior)를 적용한 준모수적 계층적 선택모형(semiparametric hierarchical selection models)을 소개한다. 여기서 제시된 준모수적 계층적 선택모형을 베이지안 방법으로 추정하기 위하여 마코프 연쇄 몬테칼로(Markov chain Monte Carlo)방법을 이용한다. 제시된 방법을 적용하기 위하여 실제 자료(Johnson, 1993)인 충치를 예방하기 위한 두 가지의 예방약의 효과에 대한 차이를 비교하기 위해 얻어진 12개의 연구를 이용하여 메타분석을 한다.

• Journal of the Korean Statistical Society
• /
• 제29권4호
• /
• pp.395-405
• /
• 2000

This article addresses the Bayesian hypothesis testing for the comparison of two exponential mans. Conventional Bayes factors with improper non-informative priors are into well defined. The fractional Byes factor(FBF) of O'Hagan(1995) is used to overcome such as difficulty. we derive proper intrinsic priors, whose Bayes factors are asymptotically equivalent to the corresponding FBFs. We demonstrate our results with three examples.

• 품질경영학회지
• /
• 제23권2호
• /
• pp.53-67
• /
• 1995

The problem considered here is to find the optimal discriminant analysis method in growth curve model. It has been studied how to find correct prior probability for the effective classification in discriminant analysis. We use the balanced condition to calculate prior probability. From the informative simulation study, new classification rule for the growth curve model is suggested. The suggested classification rule has better classification result than the other previously suggested method in terms of error rate criterion.

• Communications for Statistical Applications and Methods
• /
• 제15권1호
• /
• pp.13-26
• /
• 2008

Inference on the present data will be more reliable when the data arising from previous similar studies are available. The data arising from previous studies are referred as historical data. The power prior is defined by the likelihood function based on the historical data to the power $a_0$, where $0\;{\le}\;a_0\;{\le}\;1$. The power prior is a useful informative prior for Bayesian inference such as model selection and model comparison. We utilize the historical data to perform multiple comparison in the one-way ANOVA model. We demonstrate our results with some simulated datasets under a simple order restriction between the treatments.

• Communications for Statistical Applications and Methods
• /
• 제11권3호
• /
• pp.619-629
• /
• 2004

Binomial group testing or composite sampling is often used to estimate the proportion, p, of positive(infects, defectives) in a population when that proportion is known to be small; the potential benefits of group testing over one-at-a-time testing are well documented. The literature has focused on maximum likelihood estimation. We provide two Bayes estimators and compare them with the MLE. The first of our Bayes estimators uses an uninformative Uniform (0, 1) prior on p; the properties of this estimator are poor. Our second Bayes estimator uses a much more informative prior that recognizes and takes into account key aspects of the group testing context. This estimator compares very favorably with the MSE, having substantially lower mean squared errors in all of the wide range of cases we considered. The priors uses a Beta distribution, Beta ($\alpha$, $\beta$), and some advice is provided for choosing the parameter a and $\beta$ for that distribution.

• Journal of the Korean Data and Information Science Society
• /
• 제22권6호
• /
• pp.1265-1273
• /
• 2011

This article deals with the problem of testing the equality of the location parameters in the half-normal distributions. We propose Bayesian hypothesis testing procedures for the equality of the location parameters under the noninformative prior. The non-informative prior is usually improper which yields a calibration problem that makes the Bayes factor to be defined up to arbitrary constants. This problem can be deal with the use of the fractional Bayes factor or intrinsic Bayes factor. So we propose the default Bayesian hypothesis testing procedures based on the fractional Bayes factor and the intrinsic Bayes factors under the reference priors. Simulation study and an example are provided.

• 한국수자원학회논문집
• /
• 제49권6호
• /
• pp.481-493
• /
• 2016

본 연구에서는 최근 기후변화로 인한 집중호우의 발생횟수의 경향을 확률적으로 분석함에 있어 1개월 동안 80 mm/day 이상의 강우사상을 집중호우로 정의하여, 대구 및 부산 강우관측소로부터 수집된 384개월 동안의 집중호우를 분석하였다. 집중호우 월별 발생횟수와 같은 형식의 자료의 확률적 분석은 대개 Poisson 분포 (POI)가 사용되나 자료에 포함된 0자료의 과잉은 확률분포를 왜곡시키는 문제를 발생시킨다. 본 연구에서는 이 문제를 개선하기 위하여 개발된 일반화 Poisson 확률분포 (GPD), 0-과잉 Poisson 확률분포 (ZIP), 0-과잉 일반화 Poisson 확률분포 (ZIGP), Bayesian 0-과잉 일반화 Poisson 확률분포 (Bayesian ZIGP)를 집중호우 자료에 적용하고, 5개 모형의 특성을 비교분석하였으며, Bayesian ZIGP 모형의 구축에 있어서는 정보적 사전분포를 사용함으로써 모형의 정확도를 개선하였다. 분석결과 분석하고자 하는 자료에 0이 과다하게 포함되어 있는 경우 POI 및 GPD 분포는 관측결과와는 다른 결과를 제시하여 적절한 모형으로 고려되지 못함을 알 수 있었다. 5가지 모형 중 정보적 사전분포를 탑재한 Bayesian ZIGP 모형이 가장 관측 자료와 유사한 결과를 도출하였으나 모형의 구축에 수반되는 실용적인 측면을 고려하면 ZIP 모형도 충분히 사용될 수 있는 모형으로 추천되었다.