• Journal of the Korean Data and Information Science Society
• /
• 제22권4호
• /
• pp.811-817
• /
• 2011

We shall introduce a general probability mass function which includes several discrete probability mass functions. Especially, when the random variable X is Poisson, binomial, and negative binomial random variables as some special cases of the introduced distribution, the maximum likelihood estimator (MLE) and the uniformly minimum variance unbiased estimator (UMVUE) of the probability P(X ${\leq}$ t) are considered. And the efficiencies of the MLE and the UMVUE of the reliability ar compared each other.

• 한국음향학회지
• /
• 제21권8호
• /
• pp.735-743
• /
• 2002

본 논문에서는 세 가지 문맥독립 화자식별방법을 제안한다. 먼저, 화자 식별시 성도의 특성을 충분히 표현하지 못한 프레임이 포함되지 않도록 하는 프레임선택 (Frame Selection; FS)방법을 제안한다. 이 방법은 각 프레임에서 가장 큰 유사도와 두 번째로 큰 유사도의 차이를 평가하여 중요 프레임을 선택한 후, 선택된 프레임만을 이용하여 유사도를 계산하는 방법이다. 두 번째로 제안하는 복합 (Hyrid)방법은 FS와 가중모델순위 (Weighting Model Rank: WMR)방법을 결합시킨 것으로, FS방법을 이용하여 중요 프레임을 선택한 후, 지수함수 가중치를 이용하여 식별화자를 결정하는 것이다. 마지막으로 제안하는 수정된 가중모델순위 (Modified WMR; MWMR)방법은 식별화자를 결정할 때 유사도의 상대적 위치만을 고려하였던 기존의 U방법과는 달리 유사도와 유사도의 상대적 위치를 함께 고려하는 방법이다. 화자식별 실험결과 제안한 방법들이 기존의 ML 방법보다 향상된 식별률을 보였으며, 복합 방법 및 MWMR방법의 경우에는 WMR방법보다 각각 약 2%와 3%의 향상된 식별률을 나타내어 제안한 방법들의 유효성을 확인할 수 있었다.

• Communications for Statistical Applications and Methods
• /
• 제24권3호
• /
• pp.227-240
• /
• 2017

In this paper, we introduce the inverted exponentiated Weibull (IEW) distribution which contains exponentiated inverted Weibull distribution, inverse Weibull (IW) distribution, and inverted exponentiated distribution as submodels. The proposed distribution is obtained by the inverse form of the exponentiated Weibull distribution. In particular, we explain that the proposed distribution can be interpreted by Marshall and Olkin's book (Lifetime Distributions: Structure of Non-parametric, Semiparametric, and Parametric Families, 2007, Springer) idea. We derive the cumulative distribution function and hazard function and calculate expression for its moment. The hazard function of the IEW distribution can be decreasing, increasing or bathtub-shaped. The maximum likelihood estimation (MLE) is obtained. Then we show the existence and uniqueness of MLE. We can also obtain the Bayesian estimation by using the Gibbs sampler with the Metropolis-Hastings algorithm. We also give applications with a simulated data set and two real data set to show the flexibility of the IEW distribution. Finally, conclusions are mentioned.

• 한국국방경영분석학회지
• /
• 제11권2호
• /
• pp.69-82
• /
• 1985

In this study, we consider the simultaneous estimation of the parameters of the distribution of p independent Poisson random variables using the weighted loss function. The relation between the estimation under the weighted loss function and the case when more than one observation is taken from some population is studied. We derive an estimator which dominates Tsui and Press's estimator when certain conditions hold. We also derive an estimator which dominates the maximum likelihood estimator(MLE) under the various loss function. The risk performances of proposed estimators are compared to that of MLE by computer simulation.

• 품질경영학회지
• /
• 제25권3호
• /
• pp.51-61
• /
• 1997

We introduce a method of estimating an unknown failure rate function based on sample data. We estimate failure rate function by a function s from a space of cubic splines constrained to be linear (or constant) in tails using maximum likelihood estimation. The number of knots are determined by Bayesian Information Criterion(BIC). Examples using simulated data are used to illustrate the performance of this method.

• Journal of the Korean Statistical Society
• /
• 제30권4호
• /
• pp.563-571
• /
• 2001

In this paper, we study selecting a transformation so that the transformed variable is nearly symmetrically distributed. The large sample properties of an M-estimator of transformation parameter that is obtained by minimizing the integrated square of the imaginary part of the empirical characteristic function are investigated when a random sample is selected from some unspecified distribution. According to influence function calculations and Monte Carlo simulations, these estimates are less sensitive, than the normal model maximum likelihood estimates, to a few outliers.

• Journal of the Korean Data and Information Science Society
• /
• 제20권6호
• /
• pp.1169-1175
• /
• 2009

In this paper, the inferences of data obtained from periodic inspection and type I censoring for the step-stress accelerated life test are studied. The exponential distribution with a failure rate function that a log-linear function of stress and the tampered failure rate model are considered. The maximum likelihood estimators of the model parameters are estimated and also the optimal stress change time which minimize the asymptotic variance of maximum likelihood estimators of parameters is determined. A numerical example will be given to illustrate the proposed inferential procedures and the sensitivity of the asymptotic variance of the estimated mean by the guessed parameters is investigated.

• Journal of the Korean Data and Information Science Society
• /
• 제17권4호
• /
• pp.1375-1386
• /
• 2006

In life testing, the lifetimes of test units under the usual conditions are so long that life testing at usual conditions is impractical. Testing units are subjected to conditions of high stress to yield informations quickly. In this paper, the inferences of parameters on the three step-stress accelerated life testing are studied. The two-parameter exponential distribution with a failure rate function that a log-quadratic function of stress and the tempered failure rate model are considered. We obtain the maximum likelihood estimators of the model parameters and their confidence regions. A numerical example will be given to illustrate the proposed inferential procedures.

• Communications for Statistical Applications and Methods
• /
• 제22권3호
• /
• pp.233-239
• /
• 2015

This study compares two generalized Lindley distributions and assesses consistency between theoretical and analytical results. Data (complete and censored) assumed to follow the Lindley distribution are generated and analyzed using two generalized Lindley distributions, and maximum likelihood estimates of parameters from the generalized distributions are obtained. Size and power of tests of hypotheses on the parameters are assessed drawing on asymptotic properties of the maximum likelihood estimates. Results suggest that whereas size of some of the tests of hypotheses based on the considered generalized distributions are essentially ${\alpha}$-level, some are possibly not; power of tests of hypotheses on the Lindley distribution parameter from the two distributions differs.

• 응용통계연구
• /
• 제24권5호
• /
• pp.871-881
• /
• 2011

In this paper we propose a logistic regression method to estimate the survival function and the median survival time in interval-censored data. The proposed method is motivated by the data augmentation technique with no sacrifice in augmenting data. In addition, we develop a cross validation criterion to determine the size of data augmentation. We compare the proposed estimator with other existing methods such as the parametric method, the single point imputation method, and the nonparametric maximum likelihood estimator through extensive numerical studies to show that the proposed estimator performs better than others in the sense of the mean squared error. An illustrative example based on a real data set is given.