• Restorative Dentistry and Endodontics
• /
• 제39권2호
• /
• pp.143-147
• /
• 2014

• 응용통계연구
• /
• 제23권2호
• /
• pp.317-323
• /
• 2010

Measures are very useful tools for comparing the shape variability in statistical shape analysis. For examples, the Procrustes statistic(PS) is isolated measure, and the mean Procrustes statistic(MPS) and the root mean square measure(RMS) are overall measures. But these measures are very subjective, complicated and moreover these measures are not statistical for comparing the shape variability. Therefore we need to study some tests. It is well known that the Hotelling's $T^2$ test is used for testing shape variability of two independent samples. And for testing shape variabilities of several independent samples, instead of the Hotelling's $T^2$ test, one way analysis of variance(ANOVA) can be applied. In fact, this one way ANOVA is based on the balanced samples of equal size which is called as BANOVA. However, If we have unbalanced samples with unequal size, we can not use BANOVA. Therefore we propose the unbalanced analysis of variance(UNBANOVA) for testing shape variabilities of several independent samples of unequal size.

• 한국조리학회지
• /
• 제14권1호
• /
• pp.21-38
• /
• 2008

This research aimed to analyze the differences in financial variables classifying chain restaurants. A total of 126 samples were drawn from financial statements for $2001{\sim}2006$. As a result of analysis, there was a significant difference in Pillai's Trace, Wilks' Lambda, Hotelling's Trace, and Roy's Largest Root values at the significant probability value(p<0.05) based on F value in terms of stability among chain restaurants. Difference was found only in current rate and liabilities in ANOVA. There was a great difference in current rate among institutional restaurants, fast food restaurants, and cafeterias. There was a significant difference in Pillai's Trace, Wilks' Lambda, Hotelling's Trace, and Roy's Largest Root values at the significant probability value(p<0.05) based on F value in terms of restaurants' profitability. In ANOVA, difference was found only in net profits to net sales. It was revealed that all factors showed no significant differences in multiple comparison. All multi-variant test statistics showed a significant difference in growth and turnover. ANOVA showed a significant difference in net sales growth rate, net profit growth rate, and total assets growth rate.

• 응용통계연구
• /
• 제35권5호
• /
• pp.579-591
• /
• 2022

함수 데이터는 다양한 분야에서 수집되고 있으며, 집단 간의 함수 데이터를 비교해야하는 경우가 종종 발생한다. 이럴 경우 점별 분산분석 방법을 이용하여 설명하기에는 무리가 있으며, 통합된 결과를 제시할 필요가 있다. 이에 대한 다양한 연구가 제안되었으며, 최근에 R 패키지 fdANOVA로 구현되었다. 이 논문에서 우선 분산분석 및 다변량 분산분석을 설명하고, 최근에 제안된 다양한 단변량 및 다변량 함수 데이터 분산분석을 설명하고자 한다. 또한 R 패키지 fdANOVA의 사용 방법을 설명하고, 이 패키지를 이용하여 서울과 부산 지역의 주별 기온을 단변량 함수 데이터 분산분석을 통해 비교하고, 손글씨 이미지를 다변량 함수 데이터로 변환하여 다변량 함수 데이터 분산분석을 이용하여 비교하고자 한다.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2010년도 추계학술대회
• /
• pp.539-550
• /
• 2010

The study presents the application strategy and understanding of regression analysis with GLM(Generalized Linear Model) unifying with other statistical techniques such as correlation analysis and design of experiment(DOE). The quidelines proposed in this paper can be used for practioners to implement GLM and ANOVA(Analysis of Variance) for the DMAIC 5 steps of six sigma breakthrough.

• 한국자동차공학회논문집
• /
• 제24권3호
• /
• pp.273-278
• /
• 2016

This study makes a relative comparison of the results of tensile test and quasi-static analysis using AGL(Adjuster Guide Loop) model that plays a role in adjusting the height of shoulder belt, of the components of the vehicle seatbelt system and attempts to propose a method of reducing the error rate of the quasi-static analysis technique effectively. This study selects two major factors affecting the result of an analysis, draws the result of analysis through the method of experimental design, one of the statistical techniques and understands the contribution rate of the major factors affecting the result of the analysis through ANOVA(Analysis of Variance).

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2009년도 추계학술대회
• /
• pp.557-563
• /
• 2009

The research develops measurement processes for estimating and evaluating the gauge R&R(Reproducibility & Repeatability) using ANOVA(Analysis of Variance) of experimental design tools. The ten-step processes developed include experimental goal setting, the selection of characteristics(factors, levels), data model, ANOVA, EMS(Expected Mean Square), estimation of gauge precisions, and evaluation indexes. The three-factor combined measurement models are presented to show the processes developed in this paper.

• 한국콘텐츠학회논문지
• /
• 제7권7호
• /
• pp.133-143
• /
• 2007

본 연구의 목적은 정보품질과 서비스품질이 백화점의 서비스 만족도에 미치는 영향과 효과를 실증적으로 분석하는데 있다. 이러한 연구목적을 달성하기 위하여 문헌연구와 요인분석, 분산분석, 회귀분석을 이용한 실증적 연구를 함께 실시하였다. 본 연구의 분석결과는 다음과 같다. 첫째, 회귀분석결과 정보품질과 서비스 만족도와의 관계는 통계적 유의성이 매우 높게 분석되었다. 둘째, 분산분석에서 서비스품질에 따라 정보만족과 서비스기대치와의 관계도 유의성이 있는 것으로 나타났다. 결과적으로 정보지원체계와 서비스품질은 고객과의 관계에 있어서 주요한 요인으로 분석되었다.

• 터널과지하공간
• /
• 제32권6호
• /
• pp.386-396
• /
• 2022

로드헤더에 미치는 변수의 영향력을 분석하기 위해 픽커터 절삭시험 관련 참고문헌들을 조사하였고, 수록된 데이터들을 수집하였다. 입력 인자는 일축압축강도, 절삭 깊이, 절삭 간격, 받음각, 비틀림각, 출력 인자는 비에너지, 절삭력, 수직력으로 결정했다. 입력 인자와 출력 인자로 분류 후 실험계획법을 작성하였고 분산분석을 이용해 변수들에 대한 기여도를 조사하였다. 그 결과, 절삭력과 비에너지에 가장 큰 영향을 미치는 요인은 일축압축강도와 절삭 간격으로 분석되었다.

• Educational Technology International
• /
• 제6권2호
• /
• pp.113-130
• /
• 2005

The purpose of this study was to determine the teaching styles of professors who teach adult students in selected higher institutions. It also identified whether professors' teaching styles were teacher-centered or learner-centered and examined the relationship between instructors' teaching styles and such instructor demographic variables as gender, years of teaching experience, and taught level of courses. This study used The Principles of Adult Learning Scale(PALS) (Conti,1983) to measure instructional preferences. Demographic characteristics were collected through a personal data inventory. The analysis of variance (ANOVA) and multivariate analysis of variance (MANOVA) tests were used to analyze the data. The data were examined for significance at the .05 level of confidence by means of analysis of variance. The dependent variables in this study were teaching styles of full-time professor, as represented by the seven subscores from the standardized instrument on the PALS. The seven subscores were: (1) learner-centered activities, (2) personalizing instruction, (3) relating to experience, (4) assessing student needs, (5) climate building, (6) participation in the learning process, and (7) flexibility for personal development. The study established that there was a significant difference in mean scores on the PALS between participants when examined by the number of years of teaching experiences.