http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
BAYESIAN ESTIMATION PROCEDURES IN MULTIPROCESS DISCOUNT NORMAL MODEL
Joong Kweon Sohn,Sang Gil Kang,Heon Joo Kim 한국데이터정보과학회 1995 한국데이터정보과학회지 Vol.6 No.2
A model used in the past may be altered at will in modeling for the future. For this situatiom, the multiprocess dynamic model provides a general framework. In this paper we consider the multiprocess discount normal model with parameters having a time dependent non-linear structure. This model has nice properties such as insensitivity to outliers and quick reaction to abrupt changes of pattern.
Selecting Populations Close to a Control Based on Sample Medians
Sohn, Joong Kweon,Kang, Min Soo The Korean Society for Quality Management 1989 품질경영학회지 Vol.17 No.1
In this paper we study some procedures selecting all populations close to a control based on sample medians for several double exponential populations. The cases of known and unknown control are considered. Tables needed to use the proposed rules are provided and an illustrative example is also included.
Sohn, Joong-Kweon,Ahn, Young-Seon 慶北大學校 1989 論文集 Vol.47 No.-
본 논문에서는 다변량 정규분포에서 대조보다 더 나은 모든 모집단을 포함하는 부분집합을 선택하기 위한 Bayes-P^* 절차들에 대해 제안하고, 몇가지 성질에 관해 연구하였다. 그리고 분산-공분산 행렬과 사전분포가 달라짐에 따라 절차의 유효성과 기대되는 부분집합의 크기를 몬데카를로 시뮤레이션 방법으로 비교하였다.
A Bayes Approach for Estimating the Probablity of a Correct Selection
Sohn, Joong Kweon,Kim, Yeung-Hoon 慶北大學校 1987 論文集 Vol.44 No.-
무차별 영역 선택 절차론에서 선택이 이루어진 후 올바른 선택확률(Probability of a Correct Selection, P(CS))을 알 수가 없다. 그러므로 P(CS)에 대한 추론을 하여야 한다. 본 논문에서는 얻어진 자료에만 의존하는 베이스(Bayes)방법에 의한 P(CS)의 추정에 관하여 생각하였다.
Bayesian Inference for the Two-Parameter Exponential Models : Type-II Censored Case
Sohn, Joong-Kweon,Kim, Heon-Joo The Korean Statistical Society 1995 Journal of the Korean Statistical Society Vol.24 No.2
Suppose that we have $k(k \geq 2)$ populations (or systems), say $\pi_1, \cdots, \pi_k$, to be tested. Under the type-II censored testing without replacement we consider the problem of estimating the unknown parameters of interests and the reliability for a given time t for each population. Also we compare the perfomances of the proposed Bayes estimators with another estiamtors under the Jeffrey-type noninformative prior distribution.
Bayesian Estimation Procedure in Multiprocess Non-Linear Dynamic Normal Model
Sohn, Joong-Kweon,Kang, Sang-Gil The Korean Statistical Society 1996 Communications for statistical applications and me Vol.3 No.1
In this paper we consider the multiprocess dynamic normal model with parameters having a time dependent non-linear structure. We develop and study the recursive estimation procedure for the proposed model with normality assumption. It turns out thst the proposed model has nice properties such as insensitivity to outliers and quick reaction to abrupt changes of pattern.
Convergence Diagnostics for the Gibbs Sampler
Sohn, Joong-Kweon,Kim, Heon-Joo,Kang, Sang-Gil Korean Data and Information Science Society 1996 한국데이터정보과학회지 Vol.7 No.1
The Gibbs sampler is a substantially powerful tool in Bayesian analysis. However, it is necerssary to choose the numbert of iterations and the size of random samples. This problem has been studied by many researchers. The proposed procedures by them are generally difficult to apply to a practical problem. The attraction of the sampling based approaches is their conceptual simplicity and ease of implementation for users with available computing resources but without numerical analytic efforts. In this paper we consider the problem of determining the number of iterations t, which is simple to application.
BAYESIAN ESTIMATION PROCEDURES IN MULTIPROCESS DISCOUNT NORMAL MODEL
Sohn, Joong-Kweon,Kang, Sang-Gil,Kim, Heon-Joo Korean Data and Information Science Society 1995 한국데이터정보과학회지 Vol.6 No.2
A model used in the past may be altered at will in modeling for the future. For this situation, the multiprocess dynamic model provides a general framework. In this paper we consider the multiprocess discount normal model with parameters having a time dependent non-linear structure. This model has nice properties such as insensitivity to outliers and quick reaction to abrupt changes of pattern.
Bayesian approach of prediction problems under the censored exponential models
Sohn, Joong-Kweon,Ko, Joung-Hwan 경북대학교 1992 논문집 Vol.24 No.-
본 논문의 목적은 신뢰수명모형에서 하나의 미래 관찰치 또는 미래 n' 개의 관찰지 중 p 번째 순서통계량의 예측문제를 베이스 접근방법을 통해 연구하였다. 제2절에서는 임의중단된 모형에서 신뢰수명모형인 지수분포에 사전정보 분포인 비정보사전분포, 감마사전분포를 이용해서 하나의 미래 관찰지에 대한 예측분포와 예측구간에 대하여 연구하였다. 제3절에서는 제2절에서 이용한 분포와 사전분포를 이용해서 미래 n' 개의 관찰치 중 p 번째 순서통계량에 대하여 연구하였다.