• Communications for Statistical Applications and Methods
• /
• 제26권5호
• /
• pp.463-471
• /
• 2019

The variable transformations are useful ways to guarantee the functional relationships in the model. However, the presence of outliers may undermine the accuracy of transformation. This paper deals with response transformations in the partial linear models under the existence of outliers. A new procedure for response transformation and outliers detection is proposed. The procedure uses a sequential method for identifying outliers and dynamic graphical methods for an appropriate transformation. The graphical tools make it possible to catch diagnostic information by monitoring the movement of points in the data. The procedure is illustrated with several examples. Examples show that visual clues regarding the optimal transformation, the fittness of the model and the outlyness of the observations can be checked from the series of plots.

• Asian-Australasian Journal of Animal Sciences
• /
• 제8권4호
• /
• pp.365-368
• /
• 1995

Lactation curves of dairy cows were generated using three models, namely; incomplete gamma function (model 1), polynomial inverse function (model 2) and non-linear regression (model 3). Secondary milk yield data of 27 cows which had completed 6 lactations were used in this study. Milk yield records (once a week) throughout the lactation and from the first three months of lactation were fitted to the models. Estimation of total milk yield by model 3 using the data once a week throughout the lactation resulted in smaller % bias and standard error than those generated from model 1 and 2. But, model 2 was more accurate in predicting the 305-day milk yield equivalent closer to actual yields with smaller bias % and error using partial records up to 3 months. Also, model 2 was able to estimate the time to reach peak yield close to the actual data using partial records and model 2 could be used as a tool to advise farmers on appropriate feeding and management practices to be adopted.

• Journal of Electrical Engineering and Technology
• /
• 제10권2호
• /
• pp.625-633
• /
• 2015

The effect of altitude on thermal conduction, surface temperature, and thermal radiation of partial arc was investigated on the basis of molecular gas dynamics to facilitate a deep understanding of the pollution surface discharge mechanism. The DC flashover model was consequently modified at high altitude. The validity of the modified DC flashover model proposed in this paper was proven through a comparison with the results of high-altitude simulation experiments and earlier models. Moreover, the modified model was found to be better than the earlier modified models in terms of forecasting the flashover voltage. Findings indicated that both the thermal conduction coefficient and the surface thermodynamics temperature of partial arc had a linear decrease tendency with the altitude increasing from 0 m to 3000 m, both of which dropped by approximately 30% and 3.6%, respectively. Meanwhile, the heat conduction and the heat radiation of partial arc both had a similar linear decrease of approximately 15%. The maximum error of DC pollution flashover voltage between the calculation value according to the modified model and the experimental value was within 6.6%, and the pollution flashover voltage exhibited a parabola downtrend with increasing of pollution.

• Structural Engineering and Mechanics
• /
• 제54권2호
• /
• pp.291-304
• /
• 2015

Compared with the identification of linear structures, it is more challenging to conduct identification of nonlinear structure systems, especially when the locations of structural nonlinearities are not clear in structural systems. Moreover, it is highly desirable to develop methods of parametric identification using partial measurements of structural responses for practical application. To cope with these issues, an identification method is proposed in this paper for the detection and parametric identification of structural nonlinear restoring forces using only partial measurements of structural responses. First, an equivalent linear structural system is proposed for a nonlinear structure and the locations of structural nonlinearities are detected. Then, the parameters of structural nonlinear restoring forces at the locations of identified structural nonlinearities together with the linear part structural parameters are identified by the extended Kalman filter. The proposed method simplifies the identification of nonlinear structures. Numerical examples of the identification of two nonlinear multi-story shear frames and a planar nonlinear truss with different nonlinear models and locations are used to validate the proposed method.

• Communications for Statistical Applications and Methods
• /
• 제10권1호
• /
• pp.135-144
• /
• 2003

This work is concerned with comparison of the recently developed disparity measures for the partial association model in three dimensional categorical data. Data are generated by using simulation on each term in the log-linear model equation based on the partial association model, which is a proposed method in this paper. This alternative Monte Carlo methods are explored to study the behavior of disparity measures such as the power divergence statistic I(λ), the Pearson chi-square statistic X$^2$, the likelihood ratio statistic G$^2$, the blended weight chi-square statistic BWCS(λ), the blended weight Hellinger distance statistic BWHD(λ), and the negative exponential disparity statistic NED(λ) for moderate sample sizes. We find that the power divergence statistic I(2/3) and the blended weight Hellinger distance family BWHD(1/9) are the best tests with respect to size and power.

• 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.

• Structural Engineering and Mechanics
• /
• 제21권6호
• /
• pp.659-676
• /
• 2005

The novel form of composite walling system consists of two skins of profiled steel sheeting with an in-fill of concrete. The behaviour of such walling under in-plane shear is important in order to utilise this system as shear elements in a steel framed building. Steel sheet-concrete interface governs composite action, overall behaviour and failure modes of such walls. This paper describes the finite element (FE) modelling of the shear behaviour of walls with particular emphasis on the simulation of steel-concrete interface. The modelling of complex non-linear steel-concrete interaction in composite walls is conducted by using different FE models. Four FE models are developed and characterized by their approaches to simulate steel-concrete interface behaviour allowing either full or partial composite action. Non-linear interface or joint elements are introduced between steel and concrete to simulate partial composite action that allows steel-concrete in-plane slip or out of plane separation. The properties of such interface/joint elements are optimised through extensive parametric FE analysis using experimental results to achieve reliable and accurate simulation of actual steel-concrete interaction in a wall. The performance of developed FE models is validated through small-scale model tests. FE models are found to simulate strength, stiffness and strain characteristics reasonably well. The performance of a model with joint elements connecting steel and concrete layers is found better than full composite (without interface or joint elements) and other models with interface elements. The proposed FE model can be used to simulate the shear behaviour of composite walls in practical situation.

• 대한인간공학회지
• /
• 제20권1호
• /
• pp.45-62
• /
• 2001

This study suggests a genetic algorithm-based partial least squares (GA-based PLS) method to select the design variables for building a usability model. The GA-based PLS uses a genetic algorithm to minimize the root-mean-squared error of a partial least square regression model. A multiple linear regression method is applied to build a usability model that contains the variables seleded by the GA-based PLS. The performance of the usability model turned out to be generally better than that of the previous usability models using other variable selection methods such as expert rating, principal component analysis, cluster analysis, and partial least squares. Furthermore, the model performance was drastically improved by supplementing the category type variables selected by the GA-based PLS in the usability model. It is recommended that the GA-based PLS be applied to the variable selection for developing a usability model.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2001년도 추계학술대회논문집 I
• /
• pp.319-324
• /
• 2001

Free non-linear vibration of a rotating thin ring with a constant speed is analyzed when the ring has both the in-plane and out-of-plane motions. The geometric non-linearity of displacements is considered by adopting the Lagrange strain theory for the circumferential strain. By using Hamilton's principle, the coupled non-linear partial differential equations are derived, which describe the out-of-plane and in-plane bending, extensional and torsional motions. The natural frequencies are calculated from the linearized equations at various rotational speeds. Finally, the computation results from three non-linear models are compared with those from a linear model. Based on the comparison, this study recommends which model is appropriate to describe the non- linear behavior more precisely.

• Advances in concrete construction
• /
• 제10권6호
• /
• pp.463-478
• /
• 2020

Multiple mathematical modeling for prediction of slump, compressive strength and depth of water penetration at 28 days were performed using statistical analysis for the concrete containing waste limestone powder as partial replacement of sand obtained from experimental program reported in this research. To extract experimental data, 180 concrete cubic samples with 20 different mix designs were investigated. The twenty non-linear regression models were used to predict each of the concrete properties including slump, compressive strength and water depth penetration of concrete with waste limestone powder. Evaluation of the models using numerical methods showed that the majority of models give acceptable prediction with a high accuracy and trivial error rates. The 15-term regression models for predicting the slump, compressive strength and water depth were found to have the best agreement with the tested concrete specimens.