• 응용통계연구
• /
• 제33권1호
• /
• pp.107-114
• /
• 2020

자연 재해로부터 관측되는 자료를 대상으로 재현 수준 예측 등과 같은 자료 분석을 위해 일반화 극단값 분포(generalized extreme value)가 자주 사용되어 왔다. 표본 수가 충분히 큰 경우 연속적인 블록 최댓값들은 점근적으로 일반화 극단값 분포를 따른다. 하지만 소표본인 경우 이러한 사실은 성립되지 않을 수도 있다. 본 논문에서는 이러한 문제점을 해결하기 위해 모형 적합도 검정 및 모형 선택을 통해 로그-로지스틱(log-logistic) 분포의 사용을 제안한다. 하나의 예증으로서 중국 지진 자료를 대상으로 하여 로그-로지스틱 분포를 이용하여 재현 기간별 재현 수준 예측 및 신뢰구간을 제시한다.

• 한국컴퓨터정보학회논문지
• /
• 제13권7호
• /
• pp.1-9
• /
• 2008

본 연구에서는 소프트웨어 제품을 개발하여 테스팅을 거친 후 사용자에게 인도하는 시기를 결정하는 방출문제에 대하여 연구되었다. 소프트웨어의 결함을 제거하거나 수정 작업 중에도 새로운 결함이 발생될 가능성이 있는 무한 고장수를 가진 비동질적인 포아송 과정에 기초하고 수명분포는 단위당 고장발생률이 증가하다가 감소하는 속성을 가진 로그-로지스틱 분포를 이용한 최적 방출시기에 관한 문제를 제시하여 소프트웨어 요구 신뢰도를 만족시키고 소프트웨어 개발 및 유지 총비용을 최소화시키는 최적 소프트웨어 방출 정책에 대하여 논의 되었다. 본 논문의 수치적인 예에서는 고장간격 시간자료를 적용하고 모수추정 방법은 최우추정법과 추세분석을 통하여 자료의 효율성을 입증한 후 최적 방출시기를 추정하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제26권6호
• /
• pp.1501-1511
• /
• 2015

This paper deals with the problem of testing on the equality of the scale parameters in the log-logistic distributions. We propose default Bayesian testing procedures for the scale parameters under the reference priors. The reference prior is usually improper which yields a calibration problem that makes the Bayes factor to be defined up to a multiplicative constant. Therefore, we propose the default Bayesian testing procedures based on the fractional Bayes factor and the intrinsic Bayes factor under the reference priors. To justify proposed procedures, a simulation study is provided and also, an example is given.

• 응용통계연구
• /
• 제30권5호
• /
• pp.775-791
• /
• 2017

이진 데이터는 일상 생활에서 자주 접할 수 있는 데이터이다. 이진 데이터를 회귀 분석하는 방법으로 로지스틱(Logistic), 프로빗(Probit), Cauchit, Complementary log-log 모형이 주로 쓰이는데, 이 방법 이외에도 Liu(2004)가 제시한 t 분포를 이용한 로빗(Robit) 모형, Kim 등 (2008)에서 제시한 일반화 t-link 모형을 이용한 방법 등이 있다. 유연한 분포를 이용하면 유연한 회귀 모형이 가능해지는 점에 착안하여, 이 논문에서는 Theodossiou(1998)에서 제시된 기운 일반화 t 분포 (Skewed Generalized t Distribution)의 이용하여 우도 함수를 최대로 하는 이진 데이터 회귀 모형을 소개한다. 기운 일반화 t 분포를 R glm 함수, R sgt 패키지를 연결하여 이 논문에서 제시한 방법을 R로 분석할 수 있는 방법을 소개하고, 피마 인디언(Pima Indian) 데이터를 분석한다.

• Journal of Advanced Research in Ocean Engineering
• /
• 제4권4호
• /
• pp.185-194
• /
• 2018

In this study, the extreme sloshing pressure was predicted using various statistical models: three-parameter Weibull distribution, generalized Pareto distribution, generalized extreme value distribution, and three-parameter log-logistic distribution. The estimation of sloshing impact pressure is important in design of liquid cargo tank in severe sea state. In order to get the extreme values of local impact pressures, a lot of model tests have been carried out and statistical analysis has been performed. Three-parameter Weibull distribution and generalized Pareto distribution are widely used as the statistical analysis method in sloshing phenomenon, but generalized extreme value distribution and three-parameter log-logistic distribution are added in this study. Additionally, statistical distributions are fitted to peak pressure data using three different parameter estimation methods. The data were obtained from a three-dimensional sloshing model text conducted at Seoul National University. The loading conditions were 20%, 50%, and 95% of tank height, and the analysis was performed based on the measured impact pressure on four significant panels with large sloshing impacts. These fittings were compared by observing probability of exceedance diagrams and probability plot correlation coefficient test for goodness-of-fit.

• 대한교통학회지
• /
• 제24권6호
• /
• pp.33-43
• /
• 2006

본 연구는 도로의 기능 및 통행특성. 차로수, 연평균일교통량 등을 고려하여 설계시간계수와의 관계를 살펴보고 적정 확률분포형 선정과 K값을 추정하였다 이를 위해 2005년도 상시 교통량 조사지점에서 수집된 교통자료를 이용하여 14개의 확률분포형을 적용하였다. 각 확률분포형은 최우도법을 이용하여 매개변수를 추정하였으며 각 분포형별로 매개변수 적합성 조건을 검토하였다. 적정 확률분포형의 결정은 chi-square검정을 통하여 대상 분포형의 기각유무를 판단하였으며. 그 결과에 대해 우선순위를 정하여 적정 확률분포형을 선정하였다. 그리고 각 유형별 AADT에 따른 적정 K계수를 추정하였다. 그 결과, 지방부 2차로 및 4차로. 도시부, 관광부도로의 적정 확률분포형은 각각 Pearson V, LogLogistic, LogLogistic, Extreme value 분포로 분석되었으며 적정 K계수는 각각 $0.1{\sim}0.2,\;0.09{\sim}0.14,\;0.07{\sim}0.13,\;0.1{\sim}0.2$로 추정되었다.

• International Journal of Reliability and Applications
• /
• 제13권1호
• /
• pp.19-35
• /
• 2012

This paper presents an optimum design of step-stress partially accelerated life test (PALT) plan which allows the test condition to be changed from use to accelerated condition on the occurrence of fixed number of failures. Various life distribution models such as exponential, Weibull, log-logistic, Burr type-Xii, etc have been used in the literature to analyze the PALT data. The need of different life distribution models is necessitated as in the presence of a limited source of data as typically occurs with modern devices having high reliability, the use of correct life distribution model helps in preventing the choice of unnecessary and expensive planned replacements. Truncated distributions arise when sample selection is not possible in some sub-region of sample space. In this paper it is assumed that the lifetimes of the items follow Truncated Logistic distribution truncated at point zero since time to failure of an item cannot be negative. Optimum step-stress PALT plan that finds the optimal proportion of units failed at normal use condition is determined by using the D-optimality criterion. The method developed has been explained using a numerical example. Sensitivity analysis and comparative study have also been carried out.

• Food Science and Biotechnology
• /
• 제17권3호
• /
• pp.659-663
• /
• 2008

Different statistical distribution functions were examined to find an adequate distribution function to describe the microbial contamination behavior of a Korean side dish product, seasoned soybean sprouts for different seasons and market groups. The triang distribution was the best for any market groups in winter, while the logistic distribution could describe the microbial contamination in log CFU/g for all the market groups in spring and summer. From parametric bootstrapping based on the fitted distributions, it was found that a normal distribution could describe the distribution of mean microbial count in log CFU/g for all the seasons and market groups. Statistical parameters for each season/market group are presented to estimate the confidence interval.

• Wind and Structures
• /
• 제31권4호
• /
• pp.299-309
• /
• 2020

In this study, wind data such as speeds, loads and potential of Muğla which is located in the southwest of Turkey were statistically analyzed. The wind data which consists of hourly wind speed between 2010 and 2013 years, was measured at the 10-meters height in four different ground stations (Datça, Fethiye, Marmaris, Köyceğiz). These stations are operated by The Turkish State Meteorological Service (T.S.M.S). Furthermore, wind data was analyzed by using Log-Normal and Gamma distributions, since these distributions fit better than Weibull, Normal, Exponential and Logistic distributions. Root Mean Squared Error (RMSE) and the coefficients of the goodness of fit (R²) were also determined by using statistical analysis. According to the results, extreme wind speed in the research area was 33 m/s at the Datça station. The effective wind load at this speed is 0.68 kN/㎡. The highest mean power densities for Datça, Fethiye, Marmaris and Köyceğiz were found to be 46.2, 1.6, 6.5 and 2.2 W/㎡, respectively. Also, although Log-normal distribution exhibited a good performance i.e., lower AD (Anderson - Darling statistic (AD) values) values, Gamma distribution was found more suitable in the estimation of wind speed and power of the region.

• 충청수학회지
• /
• 제26권3호
• /
• pp.441-451
• /
• 2013

In this paper, we derive recurrence relations for moments of lower generalized order statistics within a class of doubly truncated distributions. Inverse Weibull, exponentiated Weibull, power function, exponentiated Pareto, exponentiated gamma, generalized exponential, exponentiated log-logistic, generalized inverse Weibull, extended type I generalized logistic, logistic and Gumble distributions are given as illustrative examples. Further, recurrence relations for moments of order statistics and lower record values are obtained as special cases of the lower generalized order statistics, also two theorems for characterizing the general form of distribution based on single moments of lower generalized order statistics are given.