• 응용통계연구
• /
• 제16권1호
• /
• pp.55-69
• /
• 2003

일반적인 다차원 분할표 분석을 위해 고려 할 수 있는 로그 선형 모형 (log-linear model)과 순위 변수(ordered variables)가 고려된 여러 연관성 모형(association models)을 위한 가중값이 부여된 LAD(least absolute deviations) 추정량을 제안하고 추정을 위한 반복 추정법을 제안하였다. 모의실험을 통하여 제안된 LAD추정량이 최우추정량에 비해 로버스트한 성질을 갖는 다는 것을 밝히고, 이상칸 식별을 위해 많은 선행 연구들에서 인용된 자료들의 경험적 분석을 통해 제안된 추정량과 추정방법이 가질 수 있는 문제점과 특징에 관하여 토론하였다

• 한국임상수의학회지
• /
• 제26권5호
• /
• pp.401-407
• /
• 2009

In the previous article in this series we introduced the basic concepts for statistical analysis. The present review introduces hypothesis testing for continuous and categorical data for readers of the veterinary science literature. For the analysis of continuous data, we explained t-test to compare a single mean with a hypothesized value and the difference between two means from two independent samples or between two means arising from paired samples. When the data are categorical variables, the $x^2$ test for association and homogeneity, Fisher's exact test and Yates' continuity correction for small samples, and test for trend, in which at least one of the variables is ordinal is described, together with the worked examples. McNemar test for correlated proportions is also discussed. The topics covered may provide a basic understanding of different approaches for analyzing clinical data.

• 응용통계연구
• /
• 제15권1호
• /
• pp.129-137
• /
• 2002

본 논문은 개체의 반응에 영향을 미치는 독립변수들중 일부는 고정요인들이고 일부는 확률요인들로 간주되며 반응변수가 다가범주를 갖는 명목형 변수일 때, 다원분류표에서 자료를 분석하기 위한 모형으로 혼합효과모형을 제시하고 모형내 미지모수들을 추정하는 방법을 다루고 있다

• 한국재난정보학회:학술대회논문집
• /
• 한국재난정보학회 2016년 정기학술대회
• /
• pp.259-260
• /
• 2016

어린이의 경우 다른 연령층에 비해 신체적, 정신적으로 완성되지 못하여 교통사고의 가능성이 높으며, 특히 전국의 어린이 교통사고는 점진적으로 감소 추세이나 인천의 어린이 교통사고는 감소하다가 다시 증가 추세에 들어선 실정이다. 따라서 본 연구의 목적은 어린이 교통사고 심각도에 영향을 미치는 주요 요인들을 발견하고 제시하고자 하였다. 순서형 로지스틱 회귀분석을 활용하여 순서척도인 반응변수에 대한 설명변수의 오즈(Odds)를 확인하고자 하였으며 안전운전불이행, 차대사람(횡단중), 차대차(측면직각충돌)사고가 유의한 결과로 나타났다. 안전운전불이행으로 인한 사망사고와 기타사고의 오즈차이는 1.35배, 측면직각충돌로 인한 사망사고와 기타사고의 오즈차이는 1.76배 증가하는 것으로 나타났고, 횡단중인 경우에는 오히려 사망 위험도의 오즈값이 0.58배로 감소하는 것으로 나타났다.

• Journal of Information Technology Applications and Management
• /
• 제14권2호
• /
• pp.151-168
• /
• 2007

The corporate credit rating represents an assessment of the relative level of risk associated with the timely payments required by the debt obligation. In this study, the corporate credit rating model employs artificial intelligence methods including Neural Network (NN) and Case-Based Reasoning (CBR). At first we suggest three classification models, as partitioned neural networks, all of which convert multi-group classification problems into two group classification ones: Ordinal Pairwise Partitioning (OPP) model, binary classification model and simple classification model. The experimental results show that the partitioned NN outperformed the conventional NN. In addition, we put to use CBR that is widely used recently as a problem-solving and learning tool both in academic and business areas. With an advantage of the easiness in model design compared to a NN model, the CBR model proves itself to have good classification capability through the highest hit ratio in the corporate credit rating.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2004년도 추계학술대회 및 정기총회
• /
• pp.143-146
• /
• 2004

In a situation that rank order information on attribute weights is captured, two solution approaches are presented. An exact solution approach via interaction with a decision-maker pursues progressive reduction of a set of non-dominated alternatives by narrowing down the feasible attribute weights set. In approximate solution approach, on the other hand, three categories of approximate methods such as surrogate weights method, the dominance value-based decision rules, and three classical decision rules are presented and their efficacies in terms of choice accuracy are evaluated via simulation analysis. The simulation results indicate that a method, which combines an exact solution approach through interactions with the decision-maker and the dominance value-based approach is recommendable in a case that a decision is not made at a single step under imprecisely assessed weights information.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1350-1353
• /
• 1993

A fuzzy control system typically requires“tuning,”or adjuctment of the parameters defining its linguistic variables. Automating this process amounts to applying a second“metacontrol”layer to drive the controller and plant to desired performance levels. Current methods of automated tuning rely on a single crisp numeric functional to evaluate control system performance. A generalization of Box's complex algorithm allows more realistic tuning based on lexicographic aggregation of multiple ordinal scales of performance, such as effectiveness and efficiency. The method is presented and illustrated using a simple inverted pendulum control system.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권4호
• /
• pp.331-334
• /
• 2006

Original Support Vsctor Machines (SVMs) by Vapnik were used for binary classification problems. Some researchers have tried to extend original SVM to multiclass classification. However, their studies have only focused on classifying samples into nominal categories. This study proposes a novel multiclass SVM model in order to handle ordinal multiple classes. Our suggested model may use less classifiers but predict more accurately because it utilizes additional hidden information, the order of the classes. To validate our model, we apply it to the real-world bond rating case. In this study, we compare the results of the model to those of statistical and typical machine learning techniques, and another multi class SVM algorithm. The result shows that proposed model may improve classification performance in comparison to other typical multiclass classification algorithms.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2001년도 추계학술대회
• /
• pp.25-33
• /
• 2001

본 논문은 개체의 반응에 영향을 미치는 독립변수들중 일부는 고정요인들이고 일부는 확률요인들로 간주되며 반응연수가 다가범주를 갖는 명목형 변수일때, 다원분류표에서 자료를 분석하기 위한 모형으로 혼합효과 모형을 제시하고 모형내 미지모수들을 추정하는 방법을 다루고 있다.

• Industrial Engineering and Management Systems
• /
• 제1권1호
• /
• pp.73-78
• /
• 2002

In this paper, we propose a constrained optimization model for conjoint analysis (a preference decomposition technique) to improve parameter estimation by restricting the relative importance of the attributes to an extent as decided by the respondents. Quite simply, respondents are asked to provide some pairwise attribute comparisons that are then incorporated as additional constraints in a linear programming model that estimates the partial preference values. This data collection method is typical in the analytic hierarchy process. Results of a simulation study show the new model can improve the predictive accuracy in partial value estimation by ordinal east squares (OLS) regression.