• Journal of the Korean Statistical Society
• /
• 제30권3호
• /
• pp.435-451
• /
• 2001

We describe a hierarchical bayesian model to analyze multinomial nonignorable nonresponse data. Using a Dirichlet and beta prior to model the cell probabilities, We develop a complete hierarchical bayesian analysis for multinomial proportions without making any algebraic approximation. Inference is sampling based and Markove chain Monte Carlo methods are used to perform the computations. We apply our method to the dta on body mass index(BMI) and show the model works reasonably well.

• Communications for Statistical Applications and Methods
• /
• 제9권1호
• /
• pp.115-128
• /
• 2002

Hierarchical models are widely used for inference on correlated parameters as a compromise between underfitting and overfilling problems. In this paper, we take a Bayesian approach to analyzing hierarchical models and suggest a Markov chain Monte Carlo methods to get around computational difficulties in Bayesian analysis of the hierarchical models. We apply the method to a real data on smoking and lung cancer which are collected from cities in China.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.176-176
• /
• 2018

This study presents a regional, probabilistic framework for estimating streamflow via spatial scaling in the Great Lakes basin, which is the largest lake system in the world. The framework follows a two-fold strategy including (1) a quadratic-programming based optimization model a priori to explore the model structure, and (2) a time-varying hierarchical Bayesian model based on insights found in the optimization model. The proposed model is developed to explore three innovations in hierarchical modeling for reconstructing historical streamflow at ungaged sites: (1) information of physical characteristics is utilized in spatial scaling, (2) a time-varying approach is introduced based on climate information, and (3) heteroscedasticity in residual errors is considered to improve streamflow predictive distributions. The proposed model is developed and calibrated in a hierarchical Bayesian framework to pool regional information across sites and enhance regionalization skill. The model is validated in a cross-validation framework along with four simpler nested formulations and the optimization model to confirm specific hypotheses embedded in the full model structure. The nested models assume a similar hierarchical Bayesian structure to our proposed model with their own set of simplifications and omissions. Results suggest that each of three innovations improve historical out-of-sample streamflow reconstructions although these improvements vary corrsponding to each innovation. Finally, we conclude with a discussion of possible model improvements considered by additional model structure and covariates.

• Communications for Statistical Applications and Methods
• /
• 제13권3호
• /
• pp.701-718
• /
• 2006

In cancer microarray experiments, the experimenter or patient which is nested in each experimenter often shows quite heterogeneous error variability, which should be estimated for identifying a source of variation. Our study describes a Bayesian method which utilizes clinical information for identifying a set of DE genes for the class of subtypes as well as assesses and examines the experimenter effect and patient effect which is nested in each experimenter as a source of variation. We propose a Bayesian multilevel mixed effect model based on analysis of covariance (ANACOVA). The Bayesian multilevel mixed effect model is a combination of the multilevel mixed effect model and the Bayesian hierarchical model, which provides a flexible way of defining a suitable correlation structure among genes.

• 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
• /
• 제29권2호
• /
• pp.155-168
• /
• 2000

Regarding to multiple comparison problem (MCP) of k normal population variances, we suggest a Bayesian method for calculating posterior probabilities for various hypotheses of equality among population variances. This leads to a simple method for obtaining pairwise comparisons of variances in a statistical experiment with a partition on the parameter space induced by equality and inequality relationships among the variances. The method is derived from the fact that certain features of the hierarchical nonparametric family of Dirichlet process priors, in general, make it amenable to solving the MCP and estimating the posterior probabilities by means of posterior simulation, the Gibbs sampling. Two examples are illustrated for the method. For these examples, the method is straightforward for specifying distributionally and to implement computationally, with output readily adapted for required comparison.

• 응용통계연구
• /
• 제20권2호
• /
• pp.229-244
• /
• 2007

국내외에서 소지역 추정에 관한 많은 연구가 진행되고 있다. 보조 자료가 충분히 있는 경우 모형기반 추정법을 사용하는 것이 일반적이며 이 중에서 계층적 베이지안(Hierarchical Bayesian: HB) 추정법이 가장 좋은 것으로 알려져 있다. 그러나 보조 자료가 충분하지 않은 경우에는 모형 기반 추정법의 사용은 제한적이다. 최근 충분한 보조 자료가 없는 경우 공간 정보를 보조 자료로 사용하는 방법이 제안되었다. 본 논문에서는 공간통계량과 베이즈 접근방법을 활용한 모형기반의 소지역 통계량들을 모형 검진방법(Diagnostic method)들을 이용하여 비교 분석하였다. 분석에 사용된 자료는 2005년도 경제활동인구 조사이며 소지역(시,군,구)통계를 추정하여 비교하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권1호
• /
• pp.1-7
• /
• 2004

본 논문에서는 필기체 숫자인식을 위해서 계층적으로 서로 다른 레벨의 정보를 표현할 수 있는 구조화된 특징들의 추출 방법과 특징들 사이에 의존도를 이용하여 분류하는 베이지안 망을 제안한다. 이러한 계층적 특징들을 추출하기 위해서 레벨 단위로 가버 필터들을 정의하고, FLD(Fisher Linear Discriminant) 척도를 이용하여 최적화된 가버 필터들을 선택한다. 계층적 가버 특징들은 최적화된 가버 특징들을 이용하여 추출되며, 하위 레벨일수록 더욱 국부적인 정보를 표현한다. 추출된 계층적 가버 특징들의 분류성능 향상을 위해서 가버 특징들 사이의 계층적 의존도를 이용하는 베이지안 망을 생성한다. 본 논문에서 제안하는 방법은 naive Bayesian 분류기, k-nearest neighbor 분류기, 그리고 신경망 분류기들과 함께 필기체 숫자인식에 적용되어 계층적 가버 특징들의 효율성과 계층적 의존도를 이용하는 베이지안 망은 분류성능을 향상시킬 수 있다는 것을 보여준다.

• Journal of the Korean Statistical Society
• /
• 제31권2호
• /
• pp.177-198
• /
• 2002

The estimation of variance components or variance ratios in linear model is an important issue in plant or animal breeding fields, and various estimation methods have been devised to estimate variance components or variance ratios. However, many traits of economic importance in those fields are observed as dichotomous or polychotomous outcomes. The usual estimation methods might not be appropriate for these cases. Recently threshold linear model is considered as an important tool to analyze discrete traits specially in animal breeding field. In this note, we consider a hierarchical Bayesian method for the threshold animal model. Gibbs sampler for making full Bayesian inferences about random effects as well as fixed effects is described to analyze jointly discrete traits and continuous traits. Numerical example of the model with two discrete ordered categorical traits, calving ease of calves from born by heifer and calving ease of calf from born by cow, and one normally distributed trait, birth weight, is provided.

• Communications for Statistical Applications and Methods
• /
• 제2권2호
• /
• pp.43-51
• /
• 1995

For the stress-strengh function, hierarchical Bayes estimations considered under squared error loss and entropy loss. In particular, the desired marginal postrior densities ate obtained via Gibbs sampler, an iterative Monte Carlo method, and Normal approximation (by Delta method). A simulation is presented.