• Journal of the Korean Data and Information Science Society
• /
• 제24권6호
• /
• pp.1199-1210
• /
• 2013

오늘날 높은 실업률은 대부분의 국가에서 중요한 문제 중의 하나이다. 한편 소지역의 노동 관련 통계에 대한 요구가 지난 몇년간 급속도로 증가하였다. 그러나 대부분의 공식통계를 생산하기 위한 표본설계는 대영역의 통계를 생산할 목적으로 설계되기 때문에 소지역의 경우 배정되는 표본조사단위수가 극히 적어 신뢰성 있는 통계 산출이 어렵다. 그리고 소지역 추정에 대한 대부분의 기존 연구들은 특정 시점에서의 추정에 국한되어 왔다. 그러나 대부분의 공식통계들은 월, 분기 또는 연 단위로 측정되는 패널자료이기 때문에 이를 고려한 추정방법이 필요하다. 본 논문에서는 패널자료의 분석을 위해 유용하게 사용되고 있는 일반화추정방정식의 비모수적 버전인 일반화커널추정방정식을 도출하여 조사시점을 고려한 소지역 실업률의 추정에 활용하는 방안을 제안한다. 모의실험을 통하여 일반화커널추정방정식 방법, 일반화추정방정식 방법 및 일반화선형모형과 비교한다. 그리고 2005년 1월부터 12월까지 경상남도 및 울산광역시의 25개 시군구의 경제활동인구조사의 패널자료에 위에서 언급한 세 가지 방법을 적용하여 해당 소지역의 월별 실업률을 추정한다.

• Communications for Statistical Applications and Methods
• /
• 제11권3호
• /
• pp.435-446
• /
• 2004

In this paper we introduced a new score generating function for the rank dispersion function in a multiple linear model. Based on the new score function, we derived the asymptotic relative efficiency, ARE(11, rs), of our score function with respect to the Wilcoxon scores for the generalized F distributions which show very flexible distributions with a variety of shape and tail behaviors. We thoroughly explored the selection of r and s of our new score function that provides improvement over the Wilcoxon scores.

• Journal of Biosystems Engineering
• /
• 제19권2호
• /
• pp.138-147
• /
• 1994

The stress relaxation and creep characteristics of fruits have usually been fit to an exponential expression based on a generalized Maxwell model and Burger's model. It is known that two to three terms in the expansion of those models are necessary to obtain a satisfactory fit to the rheological characteristics of fruits. Since four to six constants appear in the models, it is very difficult to determine their physical meaning according to the experimental conditions and levels. Therefore in order to ease the comparison of data, this study was conducted to develop the linearized rheological model of the fruit from the previous studies of stress relaxation and creep characteristics of fruits. Stress relaxation and creep characteristics were able to normalize and presented in the linear form of $t/S(t)=K_1+k_2t$ and $t/C(t)={K_1}^{\prime}+{K_2}^{\prime}t$, respectively. It was possible to compare the effects of experimental conditions and levels much easier from the linearized models developed in this study than from the generalized Maxwell model and Burger's model.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.461-471
• /
• 2017

In this paper we propose a feature selection method identifying important features in the semivarying coefficient model. One important issue in semivarying coefficient model is how to estimate the parametric and nonparametric components. Another issue is how to identify important features in the varying and the constant effects. We propose a feature selection method able to address this issue using generalized cross validation functions of the varying coefficient least squares support vector regression (LS-SVR) and the linear LS-SVR. Numerical studies indicate that the proposed method is quite effective in identifying important features in the varying and the constant effects in the semivarying coefficient model.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.663-668
• /
• 1990

This paper deals with the application of a Generalized Predictive Control (CPC) to a Pressurized Water Reactor (P.W.R) Nuclear Power Plant. Generalized Predictive Control is a sort of Explicit Self-Tuning Control. Current self-tuning algorithms lack robustness to prior choices of either dead-time (input time delay of a plant) or model order. GPC is shown by simulation studies to be superior to accepted self-tuning techniques such as minimum variance and pole-placement from the viewpoint that it is robust to prior choices of dead-time or model order. In this paper a GPC controller is designed to control the P.W.R. nuclear power rlant with varying dead-time and through the designing procedure the designer is free from the constraint of knowing the exact dead-time. The controller is constructed based on the 2nd order linear model approximated in the vicinity of operating point. To ensure that this low-order model describes the complex real dynamics well enough for control purposes, model parameters are updated on-line with a Recursive Least Squares algorithm. Simulation results are successful and show the possibilities of the GPC control application to actual plants with varying or unknown dead-time.

• 한국국방경영분석학회지
• /
• 제25권2호
• /
• pp.158-169
• /
• 1999

This paper is concerned with the application of generalized linear interactive modelling(GLIM) to the binary categorical data. To analyze the categorical data given by a contingency table, finding a good-fitting loglinear model is commonly adopted. In the case of a contingency table with a response variable, we can fit a logit model to find a good-fitting loglinear model. For a given $2^4$ contingency table with a binary response variable, we show the process of fitting a loglinear model by fitting a logit model using GLIM and SAS and then we estimate parameters to interpret the nature of associations implied by the model.

• 응용통계연구
• /
• 제28권2호
• /
• pp.221-230
• /
• 2015

전통적으로 반복 측정된 형제 쌍 연관 분석에서는 선형 혼합 모형이 사용되어 왔다. 그러나 그 모형은 관심있는 표현형과 연관된 유전자좌를 찾는 것에 있어서 검정력이 문제가 되는 것으로 지적되어 왔다. 본 연구에서 우리는 이러한 검정력 문제를 개선하는 방법으로 감마 혼합 모형을 고려하였고, 검정력과 제 1종 오류의 관점에서 선형 혼합 모형과 성능을 서로 비교하여 보았다. Genetic Analysis Workshop 13에서 제공된 자료를 이용하여 살펴본 결과, 감마 혼합 모형이 검정력에 있어서 큰 이득을 볼 수 있는 것으로 나타났다.

• 비파괴검사학회지
• /
• 제27권6호
• /
• pp.582-590
• /
• 2007

Imperfectly jointed interface serves as mechanical waveguide for elastic waves and gives rise to two distinct kinds of guided wave propagating along the interface. Contact acoustic nonlinearity (CAN) is known to plays major role in the generation of these interface waves called generalized Rayleigh waves in non-welded interface. Closed crack is modeled as non-welded interface that has nonlinear discontinuity condition in displacement across its boundary. Mathematical analysis of boundary conditions and wave equation is conducted to investigate the dispersive characteristics of the interface waves. Existence of the generalized Rayleigh wave(interface wave) in nonlinear contact interface is verified in theory where the dispersion equation for the interface wave is formulated and analyzed. It reveals that the interface waves have two distinct modes and that the phase velocity of anti-symmetric wave mode is highly dependent on contact conditions represented by linear and nonlinear dimensionless specific stiffness.

• Journal of the Korean Data and Information Science Society
• /
• 제27권6호
• /
• pp.1653-1660
• /
• 2016

Smoothly clipped absolute deviation (SCAD) penalty is known to satisfy the desirable properties for penalty functions like as unbiasedness, sparsity and continuity. In this paper, we deal with the regression function estimation and variable selection based on SCAD penalized censored regression model. We use the local linear approximation and the iteratively reweighted least squares algorithm to solve SCAD penalized log likelihood function. The proposed method provides an efficient method for variable selection and regression function estimation. The generalized cross validation function is presented for the model selection. Applications of the proposed method are illustrated through the simulated and a real example.

• Communications for Statistical Applications and Methods
• /
• 제9권2호
• /
• pp.515-520
• /
• 2002

In general, we use the hierarchical Poisson-gamma model for the Poisson data in generalized linear model. Time effect will be emphasized for the analysis of the observed data to be collected annually for the time period. An extended model with time effect for estimating the effect is proposed. In particularly, we discuss the Quasi likelihood function which is used to numerical approximation for the likelihood function of the parameter.