• Journal of the Korean Data and Information Science Society
• /
• 제8권2호
• /
• pp.143-152
• /
• 1997

본 논문에서는, Marshall-Olkin의 이변량 지수모형을 따르는 두개의 부품으로 이루어진 시스템에서 두 부품의 수명 $(X_{1},\;X_{2}$들이 이변량 1종 중단된 자료로 관찰되는 경우, $P(X_{1}\;<\;X_{2})$에 대한 최우추정량을 구하고 근사적 정 규성을 밝힌다. 그리고 그 추정량을 기초로 $P(X_{1}\;<\;X_{2})$에 대한 근사적 검정법을 제안하고, 몬테칼로 모의실험을 통하여 여러가지 상황에서 제안된 추정량의 근사적 검정력을 계산하여 비교하였다.

• 응용통계연구
• /
• 제32권1호
• /
• pp.99-109
• /
• 2019

비선형 시계열인 확률계수 자기회귀(random coefficient autoregressive; RCA) 모형에 대하여 여러 가지 방법을 이용한 추정량의 신뢰구간 비교하였다. RCA 모형에 대하여 자료의 분포를 가정하지 않아도 되는 Quasi 스코어 추정량과 Huber, Tukey, Andrew, Hempal 4가지 유계함수를 이용한 M-Quasi 스코어 추정량을 제시하였다. 이러한 추정량에 대하여 표준 붓스트랩 방법, 백분위수 붓스트랩 방법, 스튜던트화 붓스트랩 방법, 하이브리드 붓스트랩 방법을 이용한 신뢰구간을 구하였다. 모의실험을 통하여 RCA 모형의 오차항의 분포가 정규분포, 오염정규분포, 이중지수분포를 따를 때 Quasi 스코어 추정량과 M-Quasi 스코어 추정량들의 근사적 신뢰구간과 네가지 붓스트랩 방법을 이용한 신뢰구간을 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제21권5호
• /
• pp.927-934
• /
• 2010

본 논문은 점진 제1종 구간 중도절단표본과 점진 제2종 중도절단표본에서 모수를 추정하는 방법을 소개하고, 점진 제2종 중도절단표본에서 모수를 추정하는 방법을 활용하고자 점진 제1종 구간 중도절단표본에서 얻은 자료를 변환하여 모수를 추정하는 새로운 방법을 제안하였다. 척도모수가 미지인 지수 분포를 따르는 점진 제1종 구간 중도절단표본을 이용하여 점진 제2종 중도절단표본의 최대우도추정량을 사용하여 모수를 추정하였고, 모의실험을 통하여 두 방법에서 구한 추정량을 비교한 결과 본 논문에서 새로 제시한 방법을 이용하여 구한 모수의 추정량이 평균제곱오차 측면에서 더 우수한 추정량임이 나타났다.

• 품질경영학회지
• /
• 제25권3호
• /
• pp.96-107
• /
• 1997

The recent stream to reliability prediction is that it is totally inclusive in depth to consider even the operating and environmental condition at the level of finished goods as well as component itselves. In this study, firstly we present the reliability prediction methods by entire failure rate model which failure rate at the system level is added to the failure rate model at the component level. Secondly we build up the improved bases of reliability demonstration through a, pp.ication of Kaplan-Meier, Cumulative hazard, Johnson's methods as non-parametric and Maximum Likelihood Estimator under exponential & Weibull distribution as parametric. And also present the methods of curve fitting to piecewise failure rate under Weibull distribution, PRST (Probability Ratio Sequential Test), curve fitting to S-shaped reliability growth curve, computer programs of each methods. Lastly we show the practical for determination of optimal burn-in time as a method of reliability enhancement, and also verify the practical usefulness of the above study through the a, pp.ication of failure and test data during 1 year.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2000년도 추계학술발표회 논문집
• /
• pp.235-240
• /
• 2000

In this paper a test of fit for exponentiality and we propose the estimator of Kullback-Leibler Information functions using the data from accelerated life tests. This acceleration model is assumed to be a tampered random variable model. The procedure is applicable when the exponential parameter based on the data from accelerated life tests is or is not specified under null hypothesis. Using Simulations, the power of the proposed test based on use condition of accelerated life test under alternatives is compared with that of other standard tests in the small sample.

• 대한산업공학회지
• /
• 제19권2호
• /
• pp.15-21
• /
• 1993

This paper considers the optimal design of accelerated life test in which the stress is linearly increased. It discusses the special case when the life distribution under constant stress follows an exponential distribution and the accelerated equation satisfies the inverse power law. It is assumed that cumulative damage is linear, that is, the remaining life of test units depends only on the current cumulative fraction failed and current stress(cumulative exposure model). The optimization criterion is the asymptotic variance of the maximum likelihood estimator of the log mean life at a design stress. The optimal increasing rate is obtained to minimize the asymptotic variance. Table of sensitivity analysis is given for the prior estimators of model parameters.

• Journal of the Korean Statistical Society
• /
• 제18권2호
• /
• pp.125-134
• /
• 1989

This paper presents optimum simple step-stress accelerated life test plans for the case where the test process is observed periodically at intervals of the same length. Two types of failure data, periodically observed complete data and periodically observed censored data, are considered. An exponential life distribution with a mean that is a log-linear function of stress, and a cumulative exposure model for the effect of changing stress are assumed. For each type of data, the optimum test plan which minimizes the asymptotic variance of the maximum likelihood estimator of the mean life at a design stress is obtained and its behaviors are studied.

• Communications for Statistical Applications and Methods
• /
• 제6권1호
• /
• pp.89-98
• /
• 1999

In this paper we estimate the reliability of parallel system with two components. We assume that the strengths of these components follow bivariate exponential(BVE) models proposed by Marshall-Olkin(1967) Block-Basu(1974) Freund(1961) and Proschan-Sullo(1974) These two components are subjected to a normally distributed random stress which is independent of the strength of the components. If the strengths ($\textit{X}_1$, $\textit{X}_2$) are subjected to a stress($\textit{Y}$) then the system reliability ($\textit{R}$) is given by $\textit{R}=\textit{P}[\textit{Y} We present some numerical results and compare the bias and the mean square error of the maximum likelihood estimator and proposed estimators for a moderate sized samples when $(\textit{X}_1, \textit{X}_2)$ follow BVE of Marshall-Olkin.

• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.271-280
• /
• 2015

In this paper, the maximum likelihood estimators for parameters are derived under three step-stress accelerated life tests for Type-I hybrid censored data. The exponential distribution and the cumulative exposure model are considered based on the assumption that a log quadratic relationship exits between stress and the mean lifetime ${\theta}$. The test plan to search optimal stress change times minimizing the asymptotic variance of maximum likelihood estimators are presented. A numerical example to illustrate the proposed inferential procedures and some simulation results to investigate the sensitivity of the optimal stress change times by the guessed parameters are given.

• Journal of the Korean Statistical Society
• /
• 제28권1호
• /
• pp.73-92
• /
• 1999

In Bayesian model selection or testing problems, one cannot utilize standard or default noninformative priors, since these priors are typically improper and are defined only up to arbitrary constants. The resulting Bayes factors are not well defined. A recently proposed model selection criterion, the intrinsic Bayes factor overcomes such problems by using a part of the sample as a training sample to get a proper posterior and then use the posterior as the prior for the remaining observations to compute the Bayes factor. Surprisingly, such Bayes factor can also be computed directly from the full sample by some proper priors, namely intrinsic priors. The present paper explains how to derive intrinsic priors for simple tree ordered exponential means. Some numerical results are also provided to support theoretical results and compare with classical methods.