• Communications for Statistical Applications and Methods
• /
• 제22권5호
• /
• pp.475-485
• /
• 2015

Similar to regression, many measures to detect influential data points in discriminant analysis have been developed. Many follow similar principles as the diagnostic measures used in linear regression in the context of discriminant analysis. Here we focus on the impact on the predicted classification posterior probability when a data point is omitted. The new method is intuitive and easily interpretable compared to existing methods. We also propose a graphical display to show the individual movement of the posterior probability of other data points when a specific data point is omitted. This enables the summaries to capture the overall pattern of the change.

• 산업경영시스템학회지
• /
• 제15권25호
• /
• pp.97-101
• /
• 1992

This paper proposes a new procedures for assessing the influence of individual or groups of cases when any regressors are included. At first, various influence measures pickout influential cases when one regress-or is deleted. Next find influential subsets by using heuristic approach and perform group deletion. Retaining or removing any regressors may depend on the presence or absence of one or few cases. Then, we can identify the interrelationships that exist among regressors and cases and examine their impact on the fitted regression equation. We conclude with an example using fuel consumption data.

• 한국복식학회:학술대회논문집
• /
• 한국복식학회 2003년도 International Costume Conference
• /
• pp.68-68
• /
• 2003

Recently, street fashion has been regularly introduced in many fashion media because both consumers and marketers began to recognize the importance of street fashion as a meaningful and objective fashion information source. As the globalization proceeds in fashion field,' the street fashion informations in major cities which has led world fashion trends become more influential on domestic fashion, but little concern has been paid on it. This study classified women's street fashion in 4 major world fashion cities such as Paris, London, New York, Tokyo and identified style characteristics of each group. For data collection, 795 front-view photos were selected from the two fashion trade publication 'STREET' and 'VIEW' which has introduced street fashion photos in those cities from 1996. Classification process went on three stages: sorting, naming and grouping. 49 undergraduate students were divided into 12 teams and about 80 photos were given to each team to sort into several sub-groups by overall images or common style characteristics. Then each sub-group was named according to common images or characteristics. Final groups came out after grouping each sub-group with a similar or same title together. For each group, common style characteristics were analyzed.

• Journal of Preventive Medicine and Public Health
• /
• 제18권1호
• /
• pp.149-156
• /
• 1985

By using Factor analysis on the variables relating to the subjective symptoms of total 56 workers, who have exposed to mixture of organic solvents at the musical instrument manufacturing plant, as experinmental group, and 70 workers, who worked in noisy working environment as control group, the study was performed. It was confirmed that the variables found in hematological figures, age specification, occupational history and physical examination have a influential factor on the subjective symptoms of both groups. It was explicated that the ratio of these to total Eigen Values showed 31.1 percent in experimental group and the control group revealed 37.7 percent.

• 대한지역사회영양학회지
• /
• 제21권4호
• /
• pp.332-343
• /
• 2016

Objectives: Study purpose was to investigate perception on diet, diet problems and related factors among young adult women using focus group interviews (FGI) based on the Social Cognitive Theory (SCT). Methods: Eight groups of FGI were conducted with 47 female undergraduate or graduate students. Guide for FGI included questions regarding perception on optimal diet, diet problems and cognitive, behavioral, and environmental factors of SCT. FGI were video, audio-taped, transcribed and analyzed by themes and sub-themes. Results: Subjects showed irregular eating habits (skipping breakfast, irregular meal time) and selection of unhealthy foods as the main diet problems. Regarding cognitive factors related to optimal diet, subjects mentioned positive outcome expectations (e.g., health promotion, skin health, improvement in eating habits, etc.) and negative outcome expectations (e.g., annoying, hungry, expensive, taste). Factors that promoted optimal diet were mainly received from information from mobile or internet and access to menu or recipes. Factors that prevented optimal diet included influence from friends, lack of time and cooking skills. Behavioral factors for optimal diet included behavioral capability regarding snacks, healthy eating and smart food selection. Subjects mentioned mass media (mobile, internet, TV) as the influential physical environment, and significant others (parents, friends, grandparents) as the influential social environment in optimal diet. For education topics, subjects wanted to learn about healthy meals, basic nutrition, disease and nutrition, and weight control. They wanted to learn those aspects by using mobile or internet, lectures (cooking classes), campaign and events. Conclusions: Study results might be used for planning education regarding optimal diet for young adult women. Education programs need to focus on increasing positive outcome expectations (e.g., health) and behavioral capability for healthy eating and food selection, reducing negative outcome expectations (e.g., cost, taste) and barriers, making supportive environments for optimal diet, and incorporating topics and methods found in this study.

• 한국시스템다이내믹스연구
• /
• 제7권1호
• /
• pp.5-26
• /
• 2006

Ever increasing dependence of organization on information technology stimulates interactions between individuals and groups in the process of knowledge creation, which overall impies that a reciprocal mechanism lies within the structure of the growth of group intelligence. Individual's intelligence may affect the group intelligence, and vise versa. However, the level of group intelligence is not necessarily determined by the sum of individual's intelligence but the quality of the interactions among the individuals. This study thus aims to conceptually identify the dynamic structure of interactions among the factors influencing the group intelligence level, which is believed to be used as a tool to measure the difference of intelligence between groups. To achieve this goal several attempts were made. First, determinants of intelligence at indiviual level and group level and similarities and differences between individual's and group intelligence were identified from the previous research. Second, causal loop diagrams were developed, which show how individual's intelligence influences group intelligence and vise versa. Third, it was attempted to identify and interpret which feedback loops are most influential in either improving or hapering group intelligence as a whole. Since this study remains only at exploratory level, a more detailed and workable model for field applications has to be developed in the future.

• 한국정보시스템학회지:정보시스템연구
• /
• 제22권2호
• /
• pp.25-49
• /
• 2013

By virtue of the development and widespread of social network services, the importance of SNS for an individual's social capital formation as well as people's act of sharing information is increasingly highlighted. However, there are still few empirical studies on successful formation of SNS, people's attitude towards participation in SNS, and the brisk act of sharing information in the SNS as yet. This study performed an analysis that, in terms of forming the successful SNS, people's attachment to the group in SNS induces the attitude towards the participation in SNS, and the information-sharing act on the basis of the socio-psychological theory. For this purpose, this study carried out empirical study by dividing the influential factors into the attachment to online group, and attachment to the members in SNS group on the basis of trust. This study set up the component factors in trust as high-dimensional factors, and used SPSS 18.0 and SmartPLS 2.0 as analysis tools. Analysis results confirmed that group formation in SNS and people's attachment to the group were significantly influence attitude towards participation in SNS as well as information sharing behavior. This result implies that group formation in SNS plays an important role in active use of SNS.

• 고문화
• /
• 제70호
• /
• pp.35-62
• /
• 2007

송국리유적은 1974년 비파형동검이 부장된 석관묘가 발굴됨으로써 학계에 알려지기 시작하였으며, 1975년부터 시작된 본격적인 발굴조사를 통하여 한반도 청동기시대에 획기를 이루는 중요한 유적임이 확인되었다. 그러나 지금까지 공개된 송국리유적 보고문에는 전체 평면도조차 제시되지 못하고 있어 유적의 전모를 이해하기 어려운 상황이다. 따라서 본고에서는 송국리유적의 보고서와 관련 보고문을 재검토하여 발굴된 전체 유구의 배치도를 작성함으로써 연구의 기초자료를확보하였다 그리고 이러한 내용과 개별 유구및 출토유물에 대한 분석결과를 최근의 발굴.연구성과와 비교 검토함으로써 송국리유적의 시기와 성격에대한 새로운 견해를 제시하였다. 송국리유적에서는 주거지, 부속유구, 저장공, 요지, 목책렬, 녹채, 굴립주건물지 등의 생활 유구와 석관묘, 옹관묘, 토광묘 등의 분묘 유구, 그리고 대지조성면과 같은 대규모 토목공사의 증거들이 확인되었다. 이들은 유구의 분포 양상이나 유물상의 유사성 등을 통하여 볼 때 동일시기에 해당하는 것으로 판단되는데, 구체적인 시기는 방사성탄소연대 측정치에 의하여 대략 B.C. 850-550년의 범위로 산정되었다. 한편,송국리유적에서는 논농사의 집약화를 통하여 생산량을 증대시켰으며, 이러한 경제력을 바탕으로 유력자또는 유력 집단이 등장하게 되었을 것이다. 그들은 자신의 우월적 지위를 유지하고 더 많은 잉여생산물을 안전하게 보호하기 위하여 방어 취락을 형성하였으며, 이를차지하기 위한 빈번한 전쟁이 있었던 것으로추정된다. 그러나 어느 정도의 안정적인 삶을 유지하였으리라 생각되는데, 이는 인구 증가에 의한 주거 공간의 확대를 통하여 짐작할 수 있다. 결국 송국리유적은 이러한 과정을 거쳐 주변의 여러 취락과 관련을 맺으면서 그 정점에 위치하는 중심취락으로 성장하였을 것이다.

• 한국엔터테인먼트산업학회논문지
• /
• 제15권7호
• /
• pp.45-57
• /
• 2021

본 연구는 최근 현저하게 증가하고 있는 어린이들의 유튜브 이용량에 영향을 미치는 변인들에 대한 연구이다. 이를 위해, 유튜브 이용에 영향을 미치는 변인으로 이용방식, 조절능력, 콘텐츠 인식, 중재방식을 설정하고, 연령대별 이들 변인들을 비교하고 유튜브 이용량에 어떻게 영향을 미치는지를 분석하는 것을 목적으로 하고 있다. 연구결과, 연령대별 이용량은 차이가 없었으나 이용방식 중 구독채널 유무와 일반채널 이용, 조절능력, 콘텐츠 인식, 그리고 중재 방식 중 기술통제와 감독은 차이가 있는 것으로 나타났다. 이용량에 영향을 미치는 변인들은 3-4세 집단은 구독채널 유무와 감독이, 5-6세 집단은 구독유무, 조절능력, 일반채널, 부모감독, 대화지도의 순으로 나타났다. 7-9세 집단은 구독채널 유무, 조절능력, 프리미엄 서비스 가입으로 나타났다. 이러한 결과는 연령대별 유의미한 변인들의 유사성과 상이성을 발견함으로서 유튜브 이용량을 감소시키는 전략을 다르게 구사해야 한다는 것을 시사한다. 또한 그동안 덜 다루어진 어린이의 유튜브 이용방식에 대한 보다 구체적인 분류와 이들 방식들이 미치는 영향력에 대한 연구의 필요성을 제기하고 있다.

• 한국의류학회지
• /
• 제25권7호
• /
• pp.1341-1352
• /
• 2001

When segmenting consumers according to their fashion adoption behavior, it has been assumed that consumers' fashion conformity and innovativeness characteritics are negatively correlated. The purpose of this study was to examine the relationship between conformity and innovativeness and that these two attributes exist independently. The research problems of this study were to segment consumers according to the degrees of conformity and innovativeness, and to identify differences in reference groups and clothing purchasing behavior among the segments. The results of the empirical study showed that the fashion conformity and innovativeness were in and innovativeness; High conformity/High innovativeness group(HC/HI), High conformity/Low innovativeness group (HC/LI), Low conformity/High innovativeness group(LC/HI?, and Low conformity/Low innovativeness group (LC/LI). When the groups were compared in their reference groups and purchasing behavior, it was found out that HC groups were more influenced by reference groups than LC groups. When HC/LI and HC/HI groups were compared, HC/LI group was more influenced by their parents and siblings, while HC/HI group was more influenced by upper class and celebrities. Both groups were mostly influenced by friends and desirable passengers on the street. Friends and passengers were most influential to LC groups also, even though they were less influenced than HC groups. In conclusion, the fashion conformity and innovativeness were found to exist in different dimensions consisting dual structure. Thus, retailers and marketers can make their strategies more successfully if they use these two characteristics separately when segmenting consumers.