• Communications for Statistical Applications and Methods
• /
• 제2권2호
• /
• pp.20-32
• /
• 1995

The concept of positive ageing describes the adverse effects of age on the lifetime of units. Various aspects of this concept are described in terms of conditional probability distribution of residual life times, failure rates, equilibrium distributions, etc. In this paper, we will consider some partial ordering relations of life distributions under residual life functions and equilibrium distributions. Under residual life distributions, we study the relationships of IFR, NBU and NBUFR classes and that of DMRL and NBUE classes, By using WLR ordering comparison between F and its equilibrium $H_F$, we can decide if F belongs to NBUFR class.

• 한국항해항만학회지
• /
• 제43권6호
• /
• pp.413-419
• /
• 2019

항로는 선박의 통항이 빈번하고 특히, 항로의 입구부는 선박의 출입이 잦아 사고의 위험이 높은 지역이지만, 항로 단면에서의 통항분포에만 초점을 맞춘 연구가 다수였으며, 항로 통항 선박간의 시간분포에 대한 연구는 부족하였다. 이에 본 연구에서는 대상항로에서의 통항선박간의 시간 최적분포를 분석하기 위해서 1주일간의 선박의 통항현황을 조사하였다. 통항현황을 바탕으로 항로 입구부에 1개의 Gate line을 선정하고, Gate line을 통과하는 선박을 입출항, 교통량으로 구분하여 분석하였다. 대상항로의 해상교통 분석 자료를 바탕으로 입출항과 교통량으로 구분하여 항로 통항 선박간의 시간 최적 확률분포를 분석하였다. 최적 확률분포를 분석하기 위하여 경계분포, 비경계분포, 비음수분포, 고급분포로 구분하여 총 31개의 확률분포를 적용하였으며, 최적 확률분포 상위 3개를 분석하기 위하여 KS 검정을 사용하였다. 분석 결과 대상항로에서 통항 선박간의 최적 시간 확률분포는 Wakeby 분포로 분석되었으며, 도로교통 등의 선행연구에서 사용한 비음수 분포와 다르게 고급분포가 대부분을 차지하는 것으로 분석되었다. 따라서 향후 항로 통항 선박간의 시간 분포를 적용함에 있어 다른 교통 분야의 선행연구에서 사용한 대표적인 확률분포를 적용하는 것은 적합하지 않는 것으로 판단된다. 또한 실제 교통조사 시 통항 선박간의 거리와 최적 확률분포로 추정한 거리가 비교적 유사함을 확인하였다. 다만 본 연구는 대표적인 1개의 항로를 분석한 만큼 향후 다양한 항로에서의 통항 선박간의 시간간격 및 교통용량 산정 등의 후속연구가 필요한 것으로 판단된다.

• International Journal of Contents
• /
• 제2권2호
• /
• pp.17-24
• /
• 2006

The work presented in this paper is divided into two parts. The first part presents finite urn problems which generate truncated negative binomial random variables. Some combinatorial identities that arose from the negative binomial sampling and truncated negative binomial sampling are established. These identities are constructed and serve important roles when we deal with these distributions and their characteristics. Other important results including cumulants and moments of the distributions are given in somewhat simple forms. Second, the distributions of the maximum of two chi-square variables and the distributions of the maximum correlated F-variables are then derived within the negative binomial sampling scheme. Although multinomial theory applied to order statistics and standard transformation techniques can be used to derive these distributions, the negative binomial sampling approach provides more information and deeper insight regarding the nature of the relationship between the sampling vehicle and the probability distributions of these functions of chi-square variables. We also provide an algorithm to compute the percentage points of these distributions. We supplement our findings with exact simple computational methods where no interpolations are involved.

• Journal of Forest and Environmental Science
• /
• 제36권1호
• /
• pp.7-16
• /
• 2020

Tree size distribution modelling is an integral part of forest management. Most distribution yield systems rely on some flexible probability models. In this study, a simple finite mixture of two components two-parameter Weibull distribution was compared with complex four-parameter distributions in terms of their fitness to predict tree size distribution of teak (Tectona grandis Linn f) plantations. Also, a system of equation was developed using Seemingly Unrelated Regression wherein the size distributions of the stand were predicted. Generalized beta, Johnson's SB, Logit-Logistic and generalized Weibull distributions were the four-parameter distributions considered. The Kolmogorov-Smirnov test and negative log-likelihood value were used to assess the distributions. The results show that the simple finite mixture outperformed the four-parameter distributions especially in stands that are bimodal and heavily skewed. Twelve models were developed in the system of equation-one for predicting mean diameter, seven for predicting percentiles and four for predicting the parameters of the finite mixture distribution. Predictions from the system of equation are reasonable and compare well with observed distributions of the stand. This simplified mixture would allow for wider application in distribution modelling and can also be integrated as component model in stand density management diagram.

• 한국군사과학기술학회지
• /
• 제12권5호
• /
• pp.577-584
• /
• 2009

Fusion of decisions in wireless sensor networks having flexibility on energy efficiency is studied in this paper. Two representative distributions, the generalized Gaussian and $\alpha$-stable probability density functions, are used to model non-Gaussian noise channels. By incorporating noise channels into the parallel fusion model, the optimal fusion rules are represented and suboptimal fusion rules are derived by using a large signal-to-noise ratio(SNR) approximation. For both distributions, the obtained suboptimal fusion rules are same and have equivalent form to the Chair-Varshney fusion rule(CVR). Thus, the CVR does not depend on the behavior of noise distributions that belong to the generalized Gaussian and $\alpha$-stable probability density functions. The simulation results show the suboptimality of the CVR at large SNRs.

• 품질경영학회지
• /
• 제41권1호
• /
• pp.149-162
• /
• 2013

Purpose: The purpose of this study was to design of a probabilistic model for optimum manpower planning in R&D department by Montecarlo simulation. Methods: We investigate the process and the requirement of manpower planning and scheduling in R&D department. The empirical distributions of necessary time and manpower for R&D projects are developed. From the empirical distributions, we can estimate a probability distribution of optimum manpower in R&D department. A simulation method of estimating the probability distribution of optimum manpower is considered. It is a useful tool for obtaining the sum, the variance and other statistics of the distributions. Results: The real industry cases are given and the properties of the model are investigated by Montecarlo Simulation. we apply the model to the research laboratory of the global company, and investigate and compensate the weak points of the model. Conclusion: The proposed model provides various and correct information such as average, variance, percentile, minimum, maximum and so on. A decision maker of a company can easily develop the future plan and the task of researchers may be allocated properly. we expect that the productivity can be improved by this study. The results of this study can be also applied to other areas including shipbuilding, construction, and consulting areas.

• 한국전자파학회논문지
• /
• 제23권7호
• /
• pp.822-830
• /
• 2012

클러터는 레이더로 수신되는 불필요한 신호로 표적 탐지에 영향을 준다. 레이더 클러터는 진폭 분포, 주파수 스펙트럼 등과 같은 특성으로 정의되며, 이러한 특성을 충분히 고려하여 클러터 모델링 및 신호 생성이 되어야 한다. 본 논문에서는 다양한 클러터의 모델링에 광범위하게 사용되는 Weibull 분포 함수를 균일 분포 함수를 이용하여 단순화한 근사적 모델링 기법에 대하여 제안한다. 제안된 Weibull 분포 함수 근사 해에 의해 발생된 데이터가 원 Weibull 확률 밀도 함수를 만족하며, 생성 시간은 약 20 % 감소함을 실험 결과를 통하여 입증한다.

• 품질경영학회지
• /
• 제46권4호
• /
• pp.797-820
• /
• 2018

Purpose: It is to seek for an appropriate cost rate analysis methodology of credit card value propositions in Korea. For this issue, it is claimed that methodologies based on probability distribution is more suitable than methodologies based on data-mining. The analysis model constructed for the cost rate estimation is called VCPM model. Methods: The model includes two major variables denoted as S and P. S is monthly credit card usage amount. P stands for the proportion of usage amount at special merchants over the whole monthly usage amount. The distributions assumed for P are positively skewed distributions such as exponential, gamma and lognormal. The major inputs to the model are also derived from S and P, which are E(S) and the aggregate proportion of usage amount at special merchants over the total monthly usage amount. Results: When the credit card's value proposition is general discount, the VCPM model fits well and generates reasonable cost rate(denoted as R). However, it seems that the model does not work well for other types of credit cards. Conclusion: The VCPM model is reliable for calculating cost rate for credit cards with positively skewed distribution of P, which are general discount card. However, another model should be built for cards with other types of distributions of P.

• 대한수학회지
• /
• 제41권5호
• /
• pp.933-944
• /
• 2004

Packing dimension of a set is an upper bound for the packing dimensions of measures on the set. Recently the packing dimension of statistically self-similar Cantor set, which has uniform distributions for contraction ratios, was shown to be its Hausdorff dimension. We study the method to find an upper bound of packing dimensions and the upper Renyi dimensions of measures on a statistically quasi-self-similar Cantor set (its packing dimension is still unknown) which has non-uniform distributions of contraction ratios. As results, in some statistically quasi-self-similar Cantor set we show that every probability measure on it has its subset of full measure whose packing dimension is also its Hausdorff dimension almost surely and it has its subset of full measure whose packing dimension is also its Hausdorff dimension almost surely for almost all probability measure on it.

• 물과 미래
• /
• 제7권2호
• /
• pp.99-106
• /
• 1974

The records of wave heights which were observed at Muk ho and Po hang of the East Coast of Korea were analized by several probility functions. The exponential 2 parameter distribution was found as the best fit probability function to the historical distribution of wave heights by the test of goodness of fit. But log-normal 2 parameter and log-extremal type A distributions were also fit to the historical distribution, especially in the Smirnov-Kolmogorov test. Therefore, it can't be always regarded that those two distributions are not fit to the wave heiht's distribution. In the test of goodness of fit, the Chi-Square test gave very sensitive results and Smirnov-Kolmogorov test, which is a distribution free and non-parametric test, gave more inclusive results. At the next stage, the inter-relationship between the mean and the one-third wave heights, the mean and the one-=tenth wave heights, the one-third and the one-tenth wave heights, the one-third and the highest wave heights were obtained and discussed.