• Communications for Statistical Applications and Methods
• /
• 제15권6호
• /
• pp.1003-1011
• /
• 2008

Mixed-effect Poisson regression models are widely used for analysis of correlated count data such as those found in longitudinal studies. In this paper, we consider kernel extensions with semiparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• Communications for Statistical Applications and Methods
• /
• 제24권5호
• /
• pp.457-480
• /
• 2017

We develop a random partition procedure based on a Dirichlet process prior with Laplace distribution. Gibbs sampling of a Laplace mixture of linear mixed regressions with a Dirichlet process is implemented as a random partition model when the number of clusters is unknown. Our approach provides simultaneous partitioning and parameter estimation with the computation of classification probabilities, unlike its counterparts. A full Gibbs-sampling algorithm is developed for an efficient Markov chain Monte Carlo posterior computation. The proposed method is illustrated with simulated data and one real data of the energy efficiency of Tsanas and Xifara (Energy and Buildings, 49, 560-567, 2012).

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회 논문집
• /
• pp.731-736
• /
• 2005

현재 국내 주요 하천의 홍수예경보시스템 운영과 다목적댐의 홍수조절관리를 위하여 수문학적 모형의 하나인 저류함수모형(Storage Function Model)을 사용하고 있다. 저류함수모형은 산지가 많은 유역에 적합하도록 개발된 모형으로, 계산절차가 간편하고 홍수유출의 비선형성을 고려할 수 있는 방법이므로 선형모형보다 합리적이라고 알려져 있다. 그러나 저류함수모형을 실제 홍수유출현상에 적용하는데 있어 매개변수를 결정하는 것이 매우 어렵다. 현재 매개변수들을 결정할 수 있는 객관적이고 합리적인 방법이 제시되어 있지 않기 때문에 모형의 매개변수를 결정할 때 경험식을 이용하거나 수문기술자의 판단에 의한 보정에 의존하고 있다. 따라서, 본 논문에서는 홍수통제소에서 사용하고 있는 저류함수 모형의 대표(평균) 매개변수와 경험식, 시행착오법(trial & error method) 및 최적화기법(optimization technique) 중에 Rosenbrock 방법을 이용하여 매개변수를 산정하고 이들을 비교 분석하고자 한다.

• 한국습지학회지
• /
• 제2권1호
• /
• pp.49-58
• /
• 2000

The frequency analysis of annual maximum rainfall data and the derivation of probable rainfall intensity formula at Masan station are performed in this study. Based on the eight different rainfall duration data from 10 minutes to 24 hours, eight types of probability distribution (Gamma, Lognormal, Log-Pearson type III, GEV, Gumbel, Log-Gumbel, Weibull, and Wakeby distributions), three types of parameter estimation scheme (moment, maximum likelihood and probability weighted methods) and three types of goodness-of-fit test (${\chi}^2$, Kolmogorov-Smirnov and Cramer von Mises tests) were considered to find an appropriate probability distribution at Masan station. The Lognormal-2 distribution was selected and the probable rainfall intensity formula was derived by regression analysis. The derived formula can be used for estimating rainfall quantiles of the Masan vicinity areas with convenience and reliability in practice.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 1998년도 학술발표회 발표논문집
• /
• pp.547-551
• /
• 1998

Reaeration coefficient is the physical absorption of oxygen from the atmosphere by water. It is the most important natural means by which a stream replaces the oxygen consumed in the biodegradation of organic wastes, and the rate constant describing this process is the reaeration coefficient, It. Reaeration coefficient is the dominant parameter affecting the use of water quality model. Therefore accurate estimation of the reaeration coefficient is essential for optimum water quality management. There is several method to estimate stream reaeration coefficient. In this study, it would be concluded that SI-peak method is of practical use when applied to small stream, and CRI method is adequate to large stream.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 추계 학술발표회
• /
• pp.951-954
• /
• 2010

There are lots of soft ground improvement methods which is consist of different materials. In the analysis and design, composite ground method is usually regarded. Composite ground method considers the area replacement ratio as a key parameter to combine the physical and mechanical characteristics of tow different material. In this study, using composite material consist of three different materials which have different diameters, series of specific gravity test were performed according to KS F 2308, to investigate the applicability of composite ground method. As a result, it is found that composite material which is consist of fine grained soil and granular soil has a high applicability of composite ground method. This result means that, in estimating of ground properties of composite material which is consist of similar fine grained material such as cement mixing etc., composite ground method has a less applicability.

• 응용통계연구
• /
• 제15권2호
• /
• pp.355-366
• /
• 2002

범주형 자료의 구조파악에 주로 이용되는 로짓모형에서 비모수적 방법을 이용한 모수의 신뢰구간추정과 가설검정 등의 통계적 추론에 대하여 살펴보았다. 모수에 대한 통계적 추론에서 정규분포에 근거한 모수적 방법(Wald 방법)보다는 붓스트랩 방법이나 임의순열을 활용한 비모수적 방법이 많이 활용되고 있다. 본 연구에서는 로짓모형의 모수에 대한 비모수적 추론방법으로 붓스트랩(bootstrap)과 임의순열(random permutation)의 두 방법을 고려하고 모의실험을 통하여 가설검정의 검정력과 신뢰구간추정의 포함확률을 비교하였고 사례분석을 다루었다.

• 소성∙가공
• /
• 제12권4호
• /
• pp.408-413
• /
• 2003

Dies may have to be replaced for a number of reasons, such as changes in dimensions due to die wear or plastic deformation, deterioration of the surface finish, break down of lubrication and cracking or breakage. In this paper, die cooling methods have been suggested to improve die service life considering die wear and plastic deformation in hot forging process. The yield strength of die decreases at higher temperatures and is dependent on hardness. Also, to evaluate die life due to wear, modified Archard's wear model has been proposed by considering the thermal softening of die expressed in terms of the main tempering curve. It was found that the use of die with cooling hole was more effective than that of direct cooling method to increase the die service life for spindle component.

• 한국대기환경학회지
• /
• 제14권5호
• /
• pp.465-478
• /
• 1998

In this study, seasonal variations of the dry deposition velocity and deposition flux for the sulfur dioxide were analysed. The field observation was performed during one year (from November 1, 1995 to October 31, 1996) in Chunchon basin. The turbulence data were measured by 3-dimensional sonic anemometer/thermometer, and were estimated by mean meteorological data obtained at two heights (2.5 m and 10 m) of meteorological tower. Also, the estimation methods were evaluated by comparing the turbulence data. The results showed that the estimated dry deposition velocity and turbulence parameter such as uc and sensible heat flux using mean meteorological data were relatively similar to the sonic measurements, but all showed somewhat large differences. The dry deposition velocity was large in summer and small in winter mainly due to canopy resistance (rc). The major factor which affects diurnal variation of the velocity was aerodynamic resistance (rw). The SO2 dry deposition flux was large in winter and small in summer in Chunchon.

• The Korean Journal of Physiology and Pharmacology
• /
• 제16권2호
• /
• pp.97-106
• /
• 2012

The pharmacokinetics/pharmacodynamics analysis software NONMEM$^{(R)}$ output provides model parameter estimates and associated standard errors. However, the standard error of empirical Bayes estimates of inter-subject variability is not available. A simple and direct method for estimating standard error of the empirical Bayes estimates of inter-subject variability using the NONMEM$^{(R)}$ VI internal matrix POSTV is developed and applied to several pharmacokinetic models using intensively or sparsely sampled data for demonstration and to evaluate performance. The computed standard error is in general similar to the results from other post-processing methods and the degree of difference, if any, depends on the employed estimation options.