• 응용통계연구
• /
• 제31권6호
• /
• pp.677-692
• /
• 2018

최근 2017년 우리나라 합계출산율은 1.05명로 2005년 1.08명 수준으로 회귀하는 현상을 보이고 있다. 1.05명은 인구대체선(2.1명), 안전선(1.5명)과도 거리가 먼 초저출산 수준이고 마치 초저출산 덫에 빠질 우려가 있다. 이에 합계출산율의 합리적인 예측과 이를 통한 출산정책에 유용한 자료를 제공하는 것은 그 어느 때 보다도 중요하다. 그 동안 다양한 통계적 방법으로 합계출산율 추이를 예측하였는데, 데이터 완비성이 높고 품질이 좋은 경우 모형 접근인 모수적 방법, 데이터 추이가 단절되거나 변동이 심한 경우 평활과 가중치를 적용한 비모수적 방법, 데이터 부족과 품질 등으로 선진국의 출산율 3단계 전이현상을 참고하여 이들의 사전분포를 활용하는 베이지안 방법 등이 적용되어 왔다. 본 연구는 최근 변동이 심한 우리나라 출산율에 모수, 비모수, 그리고 베이지안 방법을 적용하여 추정과 예측을 실시하고 도출된 결과 비교를 통해 적합성과 타당성 측면에서 어떤 방법이 합리적인지 모색하고자 한다. 분석결과 합계출산율 예측값 순위는 통계청 합계출산율이 가장 높고, 베이지안, 모수, 비모수 순으로 나타났다. 2017년 TFR 1.05명 수준을 감안할 때 모수, 비모수모형으로 도출된 합계출산율 예측값이 합리적이다. 또한 출산율 자료완비성이 높고 품질이 우수할 경우 계산 효율성과 적합도 관점에서 모수적 추정과 예측 접근 방법이 타 방법보다 우수한 것으로 도출되었다.

• 한국군사과학기술학회지
• /
• 제14권5호
• /
• pp.859-870
• /
• 2011

The purpose of this paper is to develop reliability analysis procedures for repairable systems with interval failure time data and apply the procedures for assessing the storage reliability of a subsystem of a certain type of guided missile. In the procedures, the interval failure time data are converted to pseudo failure times using the uniform random generation method, mid-point method or equispaced intervals method. Then, such analytic trend tests as Laplace, Lewis-Robinson, Pair-wise Comparison Nonparametric tests are used to determine whether the failure process follows a renewal or non-renewal process. Monte Carlo simulation experiments are conducted to compare the three conversion methods in terms of the statistical performance for each trend test when the underlying process is homogeneous Poisson, renewal, or non-homogeneous Poisson. The simulation results show that the uniform random generation method is best among the three. These results are applied to actual field data collected for a subsystem of a certain type of guided missile to identify its failure process and to estimate its mean time to failure and annual mean repair cost.

• Communications for Statistical Applications and Methods
• /
• 제29권1호
• /
• pp.65-83
• /
• 2022

Although various statistical methods have been developed to map time-dependent genetic factors, most identified genetic variants can explain only a small portion of the estimated genetic variation in longitudinal traits. Gene-gene and gene-time/environment interactions are known to be important putative sources of the missing heritability. However, mapping epistatic gene-gene interactions is extremely difficult due to the very large parameter spaces for models containing such interactions. In this paper, we develop a Gaussian process (GP) based nonparametric Bayesian variable selection method for longitudinal data. It maps multiple genetic markers without restricting to pairwise interactions. Rather than modeling each main and interaction term explicitly, the GP model measures the importance of each marker, regardless of whether it is mostly due to a main effect or some interaction effect(s), via an unspecified function. To improve the flexibility of the GP model, we propose a novel grid-based method for the within-subject dependence structure. The proposed method can accurately approximate complex covariance structures. The dimension of the covariance matrix depends only on the number of fixed grid points although each subject may have different numbers of measurements at different time points. The deviance information criterion (DIC) and the Bayesian predictive information criterion (BPIC) are proposed for selecting an optimal number of grid points. To efficiently draw posterior samples, we combine a hybrid Monte Carlo method with a partially collapsed Gibbs (PCG) sampler. We apply the proposed GP model to a mouse dataset on age-related body weight.

• 응용통계연구
• /
• 제22권6호
• /
• pp.1203-1214
• /
• 2009

본 논문에서는 시계열자료의 군집분석을 위해 시간영역과 진동수영역에서의 군집 방법들을 소개하고 각 방법들의 장단점에 대해 논의하였다. KOSPI 200에 속한 15개 기업의 일별 주가자료률 이용한 비교분석 결과 비모수적인 방법인 웨이블릿을 이용한 군집분석이 가장 좋은 결과를 보였다. 비정상 시계열자료의 경우 차분 보다는 EMD를 이용하여 추세를 제거하는 방법이 스펙트럼 밀도함수를 이용한 군집분석에 더 효율적이었다.

• 한국시뮬레이션학회논문지
• /
• 제14권4호
• /
• pp.19-30
• /
• 2005

Due to explosive expansion in R & D efforts for advancement of technological predominance by Enterprises, the volume of technical information rapidly increases and emphasize on the valuation of this information has grown ever increasingly important. Therefore the requirement for systematic management and safeguard and accumulation of these intellectual properties of the Enterprise is in very high demand. A lot of effort and research has been carried out and many on going studies in progress to try to derive the optimum solution on how to manage information retention policy, processes, execution method, and hardware to execute the information with and etc. The intent of this thesis is to recommend a way for the Enterprise on how to evaluate the valuation of the data and to suggest the method on how to manage these intellectual properties by way of using Information Lifecycle Management theory which manages data according to the business valuation of the data. The decision on valuation of data and retention cycle is based on analytic method of a nonparametric regression, experimentation was carried out by applying to Enterprise Document Management System to present the suitable retention cycle according to the valuation and variety of attribute of data.

• Journal of Electrical Engineering and Technology
• /
• 제9권2호
• /
• pp.461-470
• /
• 2014

This paper presents a probabilistic power flow (PPF) analysis method for distribution network incorporating the randomness and correlation of photovoltaic (PV) generation. Based on the multivariate kernel density estimation theory, the probabilistic model of PV generation is proposed without any assumption of theoretical parametric distribution, which can accurately capture not only the randomness but also the correlation of PV resources at adjacent locations. The PPF method is developed by combining the proposed PV model and Monte Carlo technique to evaluate the influence of the randomness and correlation of PV generation on the performance of distribution networks. The historical power output data of three neighboring PV generators in Oregon, USA, and 34-bus/69-bus radial distribution networks are used to demonstrate the correctness, effectiveness, and application of the proposed PV model and PPF method.

• 산업경영시스템학회지
• /
• 제22권49호
• /
• pp.43-57
• /
• 1999

The recent trend is that risk management has more and more its importance. Neverthless, Korea's risk management is not developed. Even most banks does gap, duration in ALM for risk management, development and operation of VaR stressed at BIS have elementary level. In the case of Fallon and Pritsker, Marshall, gamma model is superior to delta model and Monte Carlo Simulation is improved at its result, as sample number is increased. And, nonparametric model is superior to parametric model. In the case of Korea's stock portfolio, VaR of Monte Carlo Simulation and Full Variance Covariance Model is less than that of Diagonal Model. The reason is that VaR of Full Variance Covariance Model is more precise than that of Diagonal Model. By the way, in the case of interest rate, result of monte carlo simulation is less than that of delta-gamma analysis on 95% confidence level. But, result of 99% is reversed. Therefore, result of which method is not dominated. It means two fact at forecast on volatility of stock and interest rate portfolio. First, in Delta-gamma method and Monte Carlo Simulation, assumption of distribution affects Value at Risk. Second, Value at Risk depends on test method. And, if option price is included, test results will have difference between the two. Therefore, If interest rate futures and option market is open, Korea's findings is supposed to like results of other advanced countries. And, every banks try to develop its internal model.

• 응용통계연구
• /
• 제31권6호
• /
• pp.761-769
• /
• 2018

통계학 연구에 모의실험이 중요하게 쓰이며 중도절단자료를 다루는 생존분석에서도 마찬가지다. 생존분석에서 Cox 모형이 널리 쓰이는데, Cox 모형을 따르는 중도절단자료를 생성하는 방법에 대해 살펴보았다. Bender 등 (Statistics in Medicine, 24, 1713-1723, 2005)은 생존시간을 생성하는 모수적 방법을 제시하였으나 생존시간뿐만 아니라 중도절단시간도 생성해야 중도절단자료를 얻게 된다. 중도절단자료를 생성하기 위한 모수적 방법과 함께 비모수적 방법도 제시하였으며 실제 자료에도 적용해 보았다.

• Nuclear Engineering and Technology
• /
• 제55권3호
• /
• pp.876-883
• /
• 2023

Radioactive waste should be solidified before being disposed of in the repository to eliminate liquidity or dispersibility. Cement is a widely used solidifying media for radioactive waste, and cement solidified waste should satisfy the minimum compressive strength of the waste acceptance criteria of a radioactive repository. Although the compressive strength of waste should be measured by the test method provided by the waste acceptance criteria, the method differs depending on the operating repository of different countries. Considering the measured compressive strength changes depending on test conditions, the effect of test conditions should be analyzed to avoid overestimation or underestimation of the compressive strength during disposal. We selected test conditions such as the height-to-diameter ratio, loading rate, and porosity as the main factors affecting the compressive strength of cement solidified radioactive waste. Owing to the large variance in measured compressive strength, the effects of the test conditions were analyzed via statistical analyses using parametric and nonparametric methods. The results showed that the test condition of the lower loading rate, with a height-to-diameter ratio of two, reflected the actual cement content well, while the porosity showed no correlation. The compressive strength assessment method that reflects the large variance of strengths was suggested.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1999년도 가을 학술발표논문집 Vol.26 No.2 (2)
• /
• pp.482-484
• /
• 1999

본 논문에서는 매개변수 없이 입력 문서 영상을 최대 동질 영역들로 분할한 다음, 각 동질 영역을 텍스트, 그림, 표 그리고 선으로 자동 분류하는 새로운 방법을 제안한다. 다단계 분석과 하향식 접근 방법을 사용하기 위하여 문서 영상을 피라미드 구조로 계층화하였으며, 어떤 영역을 분할할 지의 여부를 결정하기 위하여 그 영역의 주기성을 이용하여 판단하였다. 이러한 주기성 정보를 이용함으로써, 어떠한 매개변수 없이도 활자체 크기와 행간에 무관하게 텍스트 영역을 정확히 분석할 수 있었으며, 피라미드 구조를 만드는데 걸리는 시간이 질감 분석 접근방법보다 빠른 방법으로 설계되었다. Washington 대학의 문서 영상 데이터베이스를 이용한 실험 결과, 제안된 방법이 기존의 방법들보다 더 정확하게 문서 영상을 분할 및 분류할 수 있음을 확인할 수 있었다.