• Proceedings of the KSME Conference
• /
• 2001.11a
• /
• pp.272-277
• /
• 2001

In order to evaluate variation of fatigue data of the LP steam turbine blade steel, it is important to estimate P - S - N curves to accurately define the probability distributions. In this study, new procedure is introduced to determine the expression of P - S - N curves. For this purpose, 3-parameter Weibull distribution was found to be most appropriate among assumed distributions when the probability distributions of the fatigue life were examined by the proposed analysis. Furthermore, parameter estimation for P - S - N curves was performed using various optimization to maximize the correlation coefficient. As a result of this, sequential linear programing method is used for estimation of P - S - N curves.

• Communications for Statistical Applications and Methods
• /
• v.5 no.1
• /
• pp.85-97
• /
• 1998

완전확률화모형 및 랜덤화블럭모형하에서의 주요한 다중비교 분석기법들을 시뮬레이션을 이용하여 검토하고자 하였다. 시뮬레이션 결과는 순위변환과 최소유의차검정을 이용한 다중비교 분석기법이 모수적 ANOVA F 검정과 Fisher의 유의차검정, 비모수적 Kruskal-Wallis 검정과 최소유의차검정 및 Friedman 검정과 최소유의차검정을 이용한 분석기법보다 전체실험오차율, 전체실험검정력 및 개별쌍검정력 면에서 상대적으로 뛰어남을 보여준다. 즉 순위변환한 ANOVA F 검정의 전체실험오차율은 명목상의 유의수준을 잘 유지하고 있으며, 전체실험검정력 및 개별쌍검정력은 모수적 ANOVA F 검정과 Kruskal-Wallis 검정 및 Friedman 검정기법보다 전반적으로 우수함을 알 수 있다.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.1
• /
• pp.42-54
• /
• 2019

Crop models depend on a large number of input parameters including the cultivar parameters that represent the genetic characteristics of a given cultivar. The cultivar parameters have been estimated using high quality data for crop growth, which require considerable costs and efforts. The objective of this study was to examine the feasibility of using low quality data for the parameter estimation. In the present study, the cultivar parameters for cv. Shindongjin were estimated using the data obtained from the report of new cultivars development and research from 2005 to 2016. The root mean square errors (RMSE) of the heading dates were less than 3 days when the parameters associated with phenology were estimated. In contrast, the coefficient of determination for yield tended to be less than 0.1. The large errors incurred by the fact that no growth data collected over a season was used for parameter estimation. This suggests that detailed observation data needs to be prepared for parameter calibration, which would be aided by remote sensing approaches. The occurrence of natural disasters during a growing season has to be considered because crop models cannot take into account the effects of those events. Still, our results provide a reasonable range for the parameters, which could be used to set the boundary of a given parameter for cultivars similar to cv. Shindongjin in further studies.

• The Korean Journal of Applied Statistics
• /
• v.7 no.1
• /
• pp.35-46
• /
• 1994

We propose the nonparametric rank-like test for the location parameter in the bivariate changepoint model. Empirical powers between the parametric test and nonparametric test are compared. These results show that rank-like test is better than parametric method except bivariate normal null distribution. The point estimators for the changepoint are also compared by the empirical mean squared errors.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.261-266
• /
• 2014

When the number of parameters in the time series model are diverse, it is hard to forecast because of the increasing error by a parameter estimation. If the homogeneity hypothesis which was obtained from the same model about severeal data for the time series is selected, it is easy to get the predictive value better. Nonlinear time-series panel data for each parameter for each time series, since there are so many parameters that are present, and the large number of parameters according to the parameter estimation error increases the accuracy of the forecast deteriorated. Panel present in the time series of multiple independent homogeneity is satisfied by a comprehensive time series to estimate and to test of the parameters. For studying about the homogeneity test for the m independent non-linear of the time series panel data, it needs to set the model and to make the normal conditions for the model, and to derive the homogeneity test statistic. Finally, it shows to obtain the limit distribution according to ${\chi}^2$ distribution. In actual analysis,, we can examine the result for the homogeneity test about nonlinear time series panel data which are 2 groups of stock price data.

• Environmental and Resource Economics Review
• /
• v.14 no.2
• /
• pp.447-474
• /
• 2005

Respondents, in the willingness to pay (WTP) survey, may have preference intensity about their stated WTP values. This study elicited a post-decisional intensity measure for each observed WTP answer for gathering information on the degree of preference intensity. In order to deal with the WTP data with preference intensity, this paper considers using the Type 3 Tobit model. This is usually estimated by the parametric two-stage estimation method assuming homoskedastic and bivariate normal error structure. However, if the assumptions are not satisfied, the estimates are inconsistent. The author has tested the hypotheses of homoskedasticity and normality, and could not accept them at the 1% level. The assumptions required to estimate the parametric Type 3 model are, therefore, too strong to be satisfied. As an alternative the parametric model, this study applies a semiparametric Type 3 Tobit model. The results show that the semiparametric model significantly outperforms the parametric model, and that more importantly, the mean WTP from the parametric model is significantly different from that from the semiparametric model.

• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.605-617
• /
• 2014

Small area estimation is a statistical inference method to overcome large variance due to a small sample size allocated in a small area. A shrinkage estimator obtained by minimizing relative error(RE) instead of MSE has been suggested. The estimator takes advantage of good interpretation when the data range is large. A semiparametric estimator is also studied for small area estimation. In this study, we suggest a semiparametric shrinkage small area estimator and compare small area estimators using labor statistics.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.1-6
• /
• 2005

SAS의 PROC MIXED는 ANOVA 추정량보다 더 다양한 잔차최대우도추정법 또는 최대우도추정법으로 모수들을 추론할 수 있다. 혼합모형에 속하는 불균형중첩오차구조를 갖는 선형회귀모형에서 랜덤효과에 해당되는 그룹간의 분산과 고정효과에 해당되는 회귀계수들에 대한 신뢰구간을 구하기 위하여 대표본인 경우와 소표본인 경우에 대하여 PROC MIXED를 사용한다. 시뮬레이션을 실행한 결과, 대표본인 경우에는 모수들의 신뢰구간을 구하기 위하여 PROC MIXED를 활용할 수 있지만, 소표본인 경우에는 PROC MIXED를 사용할 경우, 그룹간 분산과 회귀계수 가운데 하나인 절편항에 대한 신뢰구간은 시뮬레이터된 신뢰계수가 명시한 신뢰계수를 지키지 못하는 것을 보인다.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.11a
• /
• pp.129-142
• /
• 2006

본 논문은 공간시계열자료가 공간의 위치와 시간의 흐름에 따라 동시에 관측되는 분야인 기상, 지질, 천문, 생태, 역학 등에서 아주 넓이 사용되고 있고 그 수요가 점차 증가하는 이 시기에 복잡한 공간시계열 중선형(STBL) 모형에 대한 모수 추정 방법 중 수치 해석적 방법인 Newton-Raphson 방법과 Kalman-Filter 방법을 비교하고, 두 가지 방법에 의한 예측력을 비교하여 보았다.

• Journal of the Korean Data and Information Science Society
• /
• v.5 no.1
• /
• pp.49-57
• /
• 1994

기존의 퍼지회귀모형은 모수의 퍼지성질에 의해 관측된 종속변수의 변동을 설명하는 방법이다. 그러나 일반적으로 종속변수에 영향을 미치는 모든 독립변수를 모형화하는 일은 불가능하므로 종속변수가 삼각퍼지숫자로 관측된 경우 모형화되지 않은 변수들의 영향을 랜덤 오차항으로 두는 퍼지확률회귀모형을 소개하고 이에 따른 모수추정법을 다룬다. 이 방법은 통계적 회귀모형의 일반화로 간주할 수 있다.