• 응용통계연구
• /
• 제25권1호
• /
• pp.67-79
• /
• 2012

우리나라 자동차보험 시장은 이미 성숙기에 접어들어 성장률이 감소하고 있는 추세이다. 이러한 시기에는 새로운 고객을 유치하는 것보다도 기존 고객을 유지하는, 즉 가입한 보험회사에 대한 충성도를 높이는 것이 새로운 마케팅 경쟁전략의 목표가 될 수 있을 것이다. 이에 본 연구에서는 개인용 자동차보험시장의 현 경쟁 환경 및 향후 변화될 환경에 맞추어 손해보험회사들이 새로운 자동차보험 마케팅 전략을 수립하는데 도움이 되는 마케팅 전략을 도출 제시하고자 한다. 이를 위하여 자동차보험 가입자를 대상으로 설문조사를 진행하였고, 일반화가법부분선형모형을 활용하여 분석을 시행하여 충성도에 영향을 주는 유의한 고객만족도 요인을 찾아내었다.

• Management Science and Financial Engineering
• /
• 제10권2호
• /
• pp.53-71
• /
• 2004

In this study, a mathematical model that shows the optimal payout policy is developed. The model is new and unique in the sense that not only continuous-time framework is used, but also both partial differential equation (PDE) and real-option approach are utilized in the derivation of optimal payouts for the first time. In the model building, non-linear demand curve for dividend payouts in the competitive capital markets is assumed. From the sensitivity analysis using traditional comparative static analysis, some useful managerial implications which are consistent with famous previous studies are derived under realistic conditions. All results in this study, however, are valid under the assumption that the opportunity costs follow geometric Brownian motion, which is widely used in economic science and finance literature.

• Structural Engineering and Mechanics
• /
• 제43권2호
• /
• pp.163-177
• /
• 2012

This paper presents a LMI(linear matrix inequality)-based fuzzy approach of modeling and active vibration control of geometrically nonlinear flexible plates with piezoelectric materials as actuators and sensors. The large-amplitude vibration characteristics and dynamic partial differential equation of a piezoelectric flexible rectangular thin plate structure are obtained by using generalized Fourier series and numerical integral. Takagi-Sugeno (T-S) fuzzy model is employed to approximate the nonlinear structural system, which combines the fuzzy inference rule with the local linear state space model. A robust fuzzy dynamic output feedback control law based on the T-S fuzzy model is designed by the parallel distributed compensation (PDC) technique, and stability analysis and disturbance rejection problems are guaranteed by LMI method. The simulation result shows that the fuzzy dynamic output feedback controller based on a two-rule T-S fuzzy model performs well, and the vibration of plate structure with geometrical nonlinearity is suppressed, which is less complex in computation and can be practically implemented.

• 대한기계학회논문집B
• /
• 제32권3호
• /
• pp.181-189
• /
• 2008

GaAs film growth process from trimethylgallium(TMGa) and tertiary-butylarsine(TBAs) using a horizontal MOCVD reactor was numerically studied to explain the experimental result that the decreasing surface reaction rate as the increasing partial pressure of group III species. Using the non-linear model based on the Langmuir isotherm which considers the adsorption and desorption of molecules, film deposition over the entire reactor scale was predicted by computational fluid dynamics (CFD) with the aid of the parameters obtained from the selective area growth (SAG) technique. CFD Results using the non-linear surface reaction model with the parameters determined from the SAG experiments predicted too high film growth rate compared to the measured values at the downstream region where the temperature was decreased abruptly. The pairs of ($k_s^n$, K) from the numerical simulations was $(2.52{\times}10K^{-6}mol/m^2/s,\;1.6{\times}10^5m^3/mol)$, whereas the experimentally determined was $(3.58{\times}10^{-5}mol/m^2/s,\;6.9{\times}10^5m^3/mol)$.

• Communications for Statistical Applications and Methods
• /
• 제30권1호
• /
• pp.65-73
• /
• 2023

Contemporary biomedical data often involve an ill-posed problem owing to small sample size and large number of multi-collinear variables. Partial least squares (PLS) method could be a plausible alternative to an ill-conditioned ordinary least squares. However, in the case of a PLS model that includes a random-effect, how to deal with a random-effect or mixed effects remains a widely open question worth further investigation. In the present study, we propose a modified multivariate PLS method implementing mixed-effect model (PLSM). The advantage of PLSM is its versatility in handling serial longitudinal data or its ability for taking a randomeffect into account. We conduct simulations to investigate statistical properties of PLSM, and showcase its real clinical application to predict treatment outcome of esthetic surgical procedures of human faces. The proposed PLSM seemed to be particularly beneficial 1) when random-effect is conspicuous; 2) the number of predictors is relatively large compared to the sample size; 3) the multicollinearity is weak or moderate; and/or 4) the random error is considerable.

• Communications for Statistical Applications and Methods
• /
• 제2권2호
• /
• pp.310-319
• /
• 1995

We represent graphically the relationship of hierachical log linear models by regarding the values of the likelihood ratio statistics as the squared norm of the corresponding vectors. Right angled triangles, tetrahedrons, and modified polyhedrons are used for graphical description. We find that the angle between the two vectors depends on the coefficient of determination and the partial coefficent of determination. Thess graphical descriptions could be applied to the model selection method.

• Journal of Pharmaceutical Investigation
• /
• 제39권5호
• /
• pp.373-379
• /
• 2009

This study was conducted to develop a pharmacokinetic-pharmacodynamic (PK/PD) model of a direct thrombin inhibitor, argatroban to predict the concentration-effect profiles in rats. Argatroban was i.v. injected to rats at 0. 2, 0.8 and 3.2 mg/kg doses (n = 4-5 per dose), and plasma drug levels were determined by a validated LC/MS/MS assay. The pharmacokinetics of argatroban was linear over the i.v. dose range studied. The thrombin time (TT) and the activated partial thromboplastin time (aPTT) were measured in rat plasma and they were found to linearly increase with increasing the dose. A 2-compartment pharmacokinetic model linked with an indirect response pharmacodynamic model was successfully utilized to evaluate the drug concentration-response relationship.

• 한국전산구조공학회논문집
• /
• 제22권3호
• /
• pp.267-275
• /
• 2009

이 논문에서는 복합재료 적층판 해석을 위해 등가단층요소와 부분-선형 층별 적층요소를 서로 연계시킨 결합요소를 제안하였다. 등가단층요소는 퇴화 쉘요소에 의해 정식화되었으며, 반면에 부분-선형 층별요소의 경우 면내변위는 부분적 선형변화로, 두께방향으로의 면외변위는 일정하다고 가정하였다. 제안된 유한요소모델은 p-수렴방식에 기초를 두고 있다. 변위장 보간을 위해 적분형 르장드르 다항식이, 수치적분을 수행하기 위해서는 가우스-로바토 적분을 각각 채택하였다. 이 연구에서는 주로 p-수렴 결합요소의 검증을 위해 다양한 형태의 유한요소 다중모델에 대해 안정된 수치해석값을 보여주는 지에 초점을 두었다. 채택한 예제는 정해를 쉽게 알고 있는 단순한 문제로 인장력을 받는 평판 또는 연직하중을 받는 캔틸레버보에 적용하여 제안된 요소의 성능을 평가하였다.

• 대한의용생체공학회:의공학회지
• /
• 제37권2호
• /
• pp.84-89
• /
• 2016

In this study, we proposed ameliorated method for region of interest (ROI) study to improve its accuracy using partial volume effect (PVE). PVE which arose in volumetric images when more than one tissue type occur in a voxel, could be used to reduce an amount of gray matter and cerebrospinal fluid within ROI of diffusion tensor image (DTI). In order to define ROIs, individual b0 image was spatially aligned to the JHU DTI-based atlas using linear and non-linear registration (http://cmrm.med.jhmi.edu/). Fractional anisotropy (FA) and mean diffusivity (MD) maps were estimated by fitting diffusion tensor model to each image voxel, and their mean values were computed within each ROI with PVE threshold. Participants of this study consisted of 20 healthy controls, 27 Alzheimer's disease and 27 normal-pressure hydrocephalus patients. The result showed that the mean FA and MD of each ROI were increased and decreased respectively, but standard deviation was significantly decreased when PVE was applied. In conclusion, the proposed method suggested that PVE was indispensable to improve an accuracy of DTI ROI study.

• 응용통계연구
• /
• 제28권2호
• /
• pp.211-219
• /
• 2015

일반화 선형혼합모델은 일반적으로 경시적 범주형 자료를 분석하는데 사용된다. 이 모델에서 임의효과는 반복 측정치들의 시간에 따른 의존성을 설명한다. 임의효과 공분산행렬의 추정은 여러가지 제약조건들 때문에 쉽지 않은 문제이다. 제약조건으로는 행렬의 모수들의 수가 많으며, 또한 추정된 공분산행렬은 양정치성을 만족하여야 한다. 이러한 제한을 극복하기 위해, 임의효과 공분산행렬의 모형화를 위한 여러가지 방법이 제안되었다: 수정 단냠레스키분해, 이동평균 단냠레스키분해와 부분 자기상관행렬을 이용한 방법이 있다. 이 논문에서 위의 제안된 방법들을 소개한다.