• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권1호
• /
• pp.97-100
• /
• 2004

We propose some properties of fuzzy multivariate analysis of variance by fuzzy vector operation with agreement index. We deals fuzzy null hypotheses and fuzzy alternative hypothesis and define the agreement index for the grades of the judgements that the hypothesis is rejection or acceptance. Finally, we provide an example to evaluate the judgements.

• International Journal of Computer Science & Network Security
• /
• 제24권4호
• /
• pp.44-50
• /
• 2024

This paper offers an overview of matrix formation and calculation techniques within the framework of General Linear Models (GLMs). It takes a sequential approach, beginning with a detailed exploration of matrix formation and calculation methods in regression analysis and univariate analysis of variance (ANOVA). Subsequently, it extends the discussion to cover multivariate analysis of variance (MANOVA). The primary objective of this study was to provide a clear and accessible explanation of the underlying matrices that play a crucial role in GLMs. Through linking, essentially different statistical methods, by fundamental principles and algebraic foundations that underpin the GLM estimation. Insights presented here aim to assist researchers, statisticians, and data analysts in enhancing their understanding of GLMs and their practical implementation in diverse research domains. This paper contributes to a better comprehension of the matrix-based techniques that can be extended to GLMs.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.363-366
• /
• 2004

We propose some properties of fuzzy multonomial analysis of variance by fuzzy vector operation with agreement index.

• 한국석유지질학회:학술대회논문집
• /
• 한국석유지질학회 1998년도 제5차 학술발표회 발표논문집
• /
• pp.10-14
• /
• 1998

A systematic methodology is developed for the electrofacies determination from wireline log data using multivariate statistical analysis. To consider corresponding contribution of each log and reduce the computational dimension, multivariate logs are transformed into a single variable through principal components analysis. Resultant principal components logs are segmented using the statistical zonation method to enhance the efficiency and quality of the interpreted results. Hierarchical cluster analysis is then used to group the segments into electrofacies. Optimal number of groups is determined on the basis of the ratio of within-group variance to total variance and core data. This technique is applied to the wells in the Korea Continental Shelf. The results of field application demonstrate that the prediction of lithology based on the electrofacies classification matches well to the core and the cutting data with high reliability This methodology for electrofacies classification can be used to define the reservoir characteristics which are helpful to the reservoir management.

• Communications for Statistical Applications and Methods
• /
• 제2권2호
• /
• pp.243-248
• /
• 1995

The problem of optimal design for a nonparametric regression with binary data is considered. The aim of the statistical analysis is the estimation of a quantal response surface in two dimensions. Bias, variance and IMSE of kernel estimates are derived. The optimal design density with respect to asymptotic IMSE is constructed.

• 응용통계연구
• /
• 제30권4호
• /
• pp.567-578
• /
• 2017

일반적으로 그룹화된 다변량자료는 다변량 분산분석(multivariate analysis of variance; MANOVA)을 사용하여 그룹 간 차이를 검정할 수 있다. 그러나 만약 다변량 분산분석의 기본적인 가정이 위배되면 이 방법은 적절하지 못하다. 이 경우 다양한 거리로부터 그룹화된 비유사성을 계산한 후 다차원척도법(multidimensional scaling; MDS), 거리분석(analysis of distance; AOD) 그리고 비모수적 기법인 순열검정(permutation test)을 적용하여 문제를 해결할 수 있다. 다차원척도법은 비유사성으로부터 개체들의 좌표를 계산해주며 거리분석은 이 좌표를 활용하여 그룹구조를 파악하는데 유용하다. 특히 비유사성의 측도로 유클리드 거리를 사용하면 거리분석은 다변량 분산분석과 수리적으로 매우 밀접한 연관관계를 맺는다. 따라서 본 연구에서는 그룹화된 비유사성에 다차원척도법과 거리분석을 적용하여 그룹 내와 그룹 간의 구조를 파악하고 순열검정을 위한 새로운 검정통계량을 제안하려 한다. 덧붙여 유클리드 거리를 활용한 비유사성을 통해 거리분석과 다변량 분산분석과의 수리적 연관성을 고찰하고자 한다.

• 보건교육건강증진학회지
• /
• 제21권2호
• /
• pp.147-165
• /
• 2004

Injury is a leading cause of death in the children and adolescent populations. In particular, more than 80％ of unintentional injury was related to risk-taking behaviors involved in diverse accidents around school and home. Therefore, educational approaches should be provided for children and adolescent populations, and schools are the essential and appropriate sites to conduct safety education. This study was conducted to identify injury prevalence and safety education at schools among middle and high school students in Korea. About 1,034 middle and high students in 28 schools participated in a self-administered survey. The target schools were selected from the stratified random sampling method throughout schools of seven metropolitan cities in Korea. The questionnaires were delivered to the vice-principals by ground mailing service and the vice-principals administered survey data collection. The questionnaire asked about safety education provided in schools, injury experience in the last year, needs for injury prevention class in school, and demographics. All survey responses were entered into SPSS worksheet. Multivariate analysis of variance (MANOVA) and descriptive discriminant analysis (DDA) were used in statistical analysis with SPSS software 11.1. Multivariate analysis of variance was conducted as a preliminary analysis of DDA. According to the result of multivariate analysis of variance, gender (man), grade (poor), living with both parents, and displaying injury prevention messages on school news board were significantly different between the injured student group and the uninjured student group (p＝ .00). These four factors also had significant effects on students' injury experience in DDA, although correlation of the four factors with injury experience was weak overall based on their canonical function coefficients. All structure coefficients of the four factors were greater than .30, which means the four factors have discriminant effects on injury prevalence. The sizes of the discriminant effects, in order, were largly from gender, grade, living with both parents, and safety message display on school news boards.

• 응용통계연구
• /
• 제20권3호
• /
• pp.475-485
• /
• 2007

본 연구의 목적은 자동차오디오에서 재생된 음향의 음질에 대한 청취자의 주관적인 선호도를 객관화된 설문 등을 통하여 측정하고 그 결과를 통계적으로 분석하여 일반화시키는 것이다. 직교배열법을 사용하여 여덟 가지 음향특성들의 조합으로 이루어진 음향 환경을 객관적으로 재현하였으며, SD 7점 척도를 사용하여 청취자의 주관적 음질 선호도를 객관화시켰다. 재생된 음향의 음질에 대한 여러 청취자들의 선호도를 다변량 분산분석법을 이용하여 분석한 후, 일반적으로 전체 음질의 선호도를 결정짓는 음향특성을 찾아냈으며, 각각의 음질 선호도에 유의한 영향을 미치는 개별 음향 특성을 찾아내었다.

• 대한교통학회지
• /
• 제33권4호
• /
• pp.368-378
• /
• 2015

본 연구는 화물운송업 종사자들의 고용형태에 따른 직업만족도 차이를 분석함이 목적이다. 본 연구는 설문항목에 대한 신뢰성 타당성 검토를 위해 신뢰성 분석과 요인분석을 실시하였다. 또한 화물자동차운송업 종사자들의 고용형태에 따른 직업만족도 차이를 살펴보기 위해 다변량 분산분석을 실시하였다. 신뢰성 분석과 요인분석 결과 설문항목들은 신뢰성과 타당성을 확보한 것으로 나타났다. 다변량 분산분석 결과 비정규직과 특수형태근로 간 직업만족도 차이는 전체 항목에서 유의하지 않은 것으로 나타났다. 한편 정규직과 비정규직 간 직업만족도 차이를 분석한 결과, 보수/소득, 업무시간, 작업조건, 복리후생, 직장안정성 항목에서 정규직의 만족도가 비정규직에 비해 유의하게 높은 것으로 나타났다. 또한 정규직과 특수형태근로 간 직업만족도 차이를 분석한 결과 보수/소득, 업무시간, 복리후생, 건강을 돌볼 여유 항목에서 정규직의 만족도가 특수형태근로에 비해 유의하게 높은 것으로 나타났다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.31-34
• /
• 1996

The extensive researches have compared the performance of neural networks(NN) with those of various statistical techniques for the classification problem. The empirical results of these comparative studies have indicated that the neural networks often outperform the traditional statistical techniques. Moreover, there are some efforts that try to combine various classification methods, especially multivariate discriminant analysis with neural networks. While these efforts improve the performance, there exists a problem violating robust assumptions of multivariate discriminant analysis that are multivariate normality of the independent variables and equality of variance-covariance matrices in each of the groups. On the contrary, cluster analysis alleviates this assumption like neural networks. We propose a new approach to classification problems by combining the cluster analysis with neural networks. The resulting predictions of the composite model are more accurate than each individual technique.