• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.65-75
• /
• 2015

본 논문에서는 전문대 및 4년제 대졸 신규취업자의 임금을 결정하는 요인을 분석하기 위해 개인수준의 인적특성 변수들과 업종수준의 특성변수들을 사용하였다. 본 논문은 개인수준의 임금이 개인수준의 인적특성 (1-수준)과 업종 수준의 산업특성 (2-수준)에 의해 영향을 받는 다층구조 (multi-level)를 가지게 된다는 점을 주목하였다. 이와 같이 위계적 자료 특성을 가지는 복수의 분석단위 구조가 되면, 전통적인 회귀분석에서와 같이 개인수준의 임금이 독립이라는 가정을 할 수 없게 된다. 따라서 본 논문에서는 개인수준의 임금에 영향을 미치는 다층구조의 특성을 가진 변수들의 영향력을 보다 타당하게 분석하기 위한 방법으로 위계선형모형 (HLM; hierarchical linear model)을 이용하였다. 주요 결과는 다음과 같다. 첫째, 개인수준과 업종수준 변수들 모두를 포함한 다중대응분석의 결과에 의하면, 개인수준의 임금이 서로 다른 그룹에 대응되는 개인 특성 변수값과 업종 특성 변수값이 그룹별로 서로 상이하여 개인특성 변수만이 아니라 업종특성 변수도 개인수준의 임금에 영향을 미치고 있다는 점이 발견되었다. 둘째, 개인수준과 업종수준 변수들 모두를 포함한 의사결정나무분석의 결과에 의하면, 개인수준의 임금에 가장 많은 영향을 미치는 변수가 업종별 임금이고, 그 다음으로는 업종별 근로시간, 연령, 성별 등의 순으로 나타났다. 이와 같이 개인수준의 임금을 결정하는 데 있어서 업종의 특성이 매우 중요한 것으로 나타났다는 점은 위계적 선형모형의 활용이 타당하다는 것을 시사하는 것이다. 셋째, 개인수준의 인적특성과 업종 수준의 산업특성 변수들을 모두 포함한 모형이 다른 모형들에 비해서 모형 적합도가 가장 개선되어 위계적 선형모형이 적합한 것으로 나타났다.

• 사상체질의학회지
• /
• 제22권3호
• /
• pp.87-97
• /
• 2010

1. Objectives: In SCM, a personal Sasang constitution must be determined accurately before any Sasang treatment. The purpose of this study is to develop an objective method for classification of Sasang constitution. 2. Methods: We collected samples from 5 centers where SCM is practiced, and applied two-stage decision tree analysis on these samples. We recruited samples from 5 centers. The collected data were from subjects whose response to herbal medicine was confirmed according to Sasang constitution. 3. Results: The two-stage decision tree model shows higher classification power than a simple decision tree model. This study also suggests that gender must be considered in the first stage to improve the accuracy of classification. 4. Conclusions: We identified important factors for classifying Sasang constitutions through two-stage decision tree analysis. The two-stage decision tree model shows higher classification power than a simple decision tree model.

• 응용통계연구
• /
• 제13권2호
• /
• pp.489-503
• /
• 2000

다양한 형태의 데이터로부터 의사 결정에 유용한 정보 및 지식을 발견하려는 일련의 데이터분석 및 모형 선정과정을 데이터 마이닝(Data Mining)이라고 할 수 있다. 데이터 마이닝의 적용 예로는 신규고객에 대한 신용평가, 고객이탈방지 등과 같은 분야에서 발생하는 스코링 문제를 들 수 있는데 신용평가에서는 신용이 나쁠 가능성을 스코어로 나타내고 스코어가 높은 고객을 대상으로 특별관리를 할 수 있을 것이며 고객이탈방지에서는 이탈가능성을 스코어로 나타내고 스코어가 높은 고객을 대상으로 이탈 방지 캠페인을 벌일 수 있을 것이다. 본 논문에서는 스코링 문제를 사후확률에 대한 모형화 문제로 파악하였다. 폴리클라스를 스코링 문제에 적용하는 방법을 소개한 후 이를 독일 신용 데이터, 국내 모 PC통신회사 데이터 및 국내 모 이동통신 데이터에 적용하였다. 스코링의 성능은 이득률을 이용하여 평가하고자 하는데 나무 모형에 비하여 폴리클라스 방법이 우수함을 확인하였다.

• 한국보육지원학회지
• /
• 제16권5호
• /
• pp.69-86
• /
• 2020

Objective: The purpose of this research was to examine the prediction models of conflict and intimacy in teacher-child relationships based on decision tree analysis. Methods: The participants were 297 preschool children from ages three to five including 166 boys and 131 girls. Teacher-child relationships were measured by the Student-Teacher Relationship Scale(STRS). Physical aggression, relational aggression, social withdrawal, and prosocial behaviors were measured by teacher ratings. Moreover, ADHD-RS(Attentive Deficit Hyperactivity Disorder Rating Scale) was used to measure ADHD. The data was analyzed with decision tree analysis. Results: According to the prediction model for teacher-child conflict, the significant predictors were physical aggression and social withdrawal. According to the prediction model for teacher-child intimacy, the significant predictors were prosocial behaviors and relational aggression. However, children's age, gender and ADHD were not significant predictors. Conclusion/Implications: The findings suggest that social behaviors may be closely related with teacher-child relationships for preschool children. Based on the results of this study, intervention suggestions were made.

• 아동학회지
• /
• 제33권2호
• /
• pp.111-127
• /
• 2012

This study compared a number of related variables according to children's stress types using the data mining method. The sample population was taken from the Korean Youth Panel Survey (KYPS) data (2688, sixth-grade elementary students). The results of the decision tree model revealed that : (1) Parental expectations in terms of study, life satisfaction, self-esteem, parental attachment, aggression, the spousal relationship, other cognition (one's own misdeeds), and study related worries were all related to parent stress. (2) Life satisfaction, study related worries, admitting one's own misdeeds, gender, other cognition (one's own misdeeds), aggression, the spousal relationship, and a sense of alienation in the school were all related to appearance stress. (3) Study related worries, parental expectations in terms of study, aggression, life satisfaction, self-esteem, parental attachment, satisfying parental expectations, parental attachment, and teacher attachment were all related to academic stress. (4) A sense of alienation in the school, mixing with peers in the school, aggression, self-esteem, other cognition (one's own misdeeds), study related worries, parental abuse, and life satisfaction were all significantly related to friend stress. These results suggested that children's diverse conditions should be considered according to the stress types if we are to understand and cope with these stress types more efficiently.

• 농촌지도와개발
• /
• 제19권3호
• /
• pp.617-647
• /
• 2012

The purpose of this study was to identify the predictors of suicidal ideation of rural residents. This study was based on predictors of suicidal ideation of urban residents. The participants were adolescents, adults, and seniors sampled from 10 provinces all over the country, from May to Aug, 2010. The data for the study were analysed as decision tree analysis. The major results of the study were as follows. First, a main predictor of suicidal ideation for rural residents was high depression. Unlike rural residents, urban residents reporting high depression and influence of mass media showed high suicidal ideation. Second, interaction of depression and family solidarity was important predictor of suicide ideation both rural and urban residents, but a condition that effects the situation differed between rural and urban residents. Rural residents reporting high depression and high family solidarity showed high suicidal ideation, urban residents reporting low depression and high family solidarity showed low suicidal ideation. Stress was also operate differently. Rural residents reporting moderate depression, low family solidarity and high stress showed high suicidal ideation, but stress of urban resident was not a important predictors of suicidal ideation. And rural residents reporting low depression and low stress showed the lowest level of suicidal ideation, urban residents reporting low family solidarity and low depression showed the lowest level of suicidal ideation.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2007년도 춘계학술논문 발표대회
• /
• pp.101-104
• /
• 2007

As the proportion of underground construction increases, the impact of inappropriate selection of a underground construction method for a construction size increases. The purpose of this study is to develop an objective way of selecting an excavation method. There have been several attempts to achieve the same goal using various data mining methods such as the artificial neural network, the support vector machine, and the case-based reasoning. However, they focused only on the selection of a retaining wall construction method out of six types of retaining walls. When we categorized an underground construction work into four groups and added more number of independent variables (i.e., more number of construction methods), the predictability decreased. As an alternative, we developed a decision tree by analyzing 25 earthwork cases with detailed information. We implemented the developed decision tree as a computer-supported program called Dr. underground and are still in the process of validating and revising the decision tree. This study is still in a preliminary stage and will be improved by collecting and analyzing more cases.

• 농촌지도와개발
• /
• 제23권3호
• /
• pp.243-255
• /
• 2016

This study aims to identify the characteristics of businesses influencing the choice of their type in the 6th industry and analyze how they work. This study analyzed data of 752 businesses certified as belonging to the 6th industry in 2015 through the classification and regression tree (CART) algorithm in decision tree analysis. The results of analysis showed that the type of agricultural product processing, region, the type of service, and the production percentage in a province affected a choice of the type. The most important variable that impacted how businesses in the 6th industry chose their type was the type of agricultural product processing, and if a business produced simple agricultural products, it was likely to specialize into $1st^*2nd$ or $1st^*3rd$. Access to large consumption areas was a critical factor in the growth of 2nd and 3rd industrial functions. These findings would contribute to establishing a model to develop the 6th industry and empirically demonstrate the importance of access to large consumption areas for agricultural businesses and rural tourism.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 추계학술발표대회
• /
• pp.1050-1053
• /
• 2014

웹 기반 서비스의 발전과 스마트 기기의 보급으로 사용자들은 다양한 웹 서비스들을 이용할 수 있게 되었고, 소셜 웹과 같은 사람들 간의 관계를 형성함으로써 정보를 주고받는 서비스에 접근하여 자신만의 콘텐츠를 생성, 공유하기가 용이해졌다. 그러나 소셜 웹 사용자들이 증가하고 지식의 양이 늘어남에 따라, 방대한 양의 지식들 중 필요한 정보만을 효율적으로 창출해내고자 하는 연구 또한 시도되어 왔다. 그러나, 기존의 방법은 다수의 서비스 사용자들의 공통적인 관심사가 반영된 결과를 도출해내기에는 부족하다는 단점이 있었다. 그리하여, 본 논문에서는 집단 지성 알고리즘과 의사 결정 나무를 활용하여 소셜 웹을 이용하는 사용자들의 태그와 URL 정보를 토대로 트렌드를 분석, 콘텐츠를 추천하는 방법을 제안하고, 이를 통하여 다수 사용자들의 기호가 반영된 다양한 정보들을 소셜 웹 사용자들에게 제공해줄 수 있음을 보인다.

• 공학교육연구
• /
• 제21권4호
• /
• pp.46-52
• /
• 2018

In general, lecture evaluation has been used in most universities as an important criterion to evaluate quality of education. This study is exploratory research on the predictors that determine lecture evaluation in college of engineering to give practical implications for improvement of engineering education. For the exploration of predictors of lecture evaluation, the data of lecture evaluation in A College of Engineering located in the metropolitan area was used, and Decision Tree Analysis was utilized as an analysis method. As a result, the characteristics of students turned out to be the most distinct predictor comparing with those of course and instructor at lecture evaluation in college of engineering. That is, as various elements other than teaching competency influence lecture evaluation in college of engineering, it is necessary to be more careful in evaluating quality of lecture or teaching competence. Thus, a follow-up study should be conducted to adjust the influence by the predictors that instructors can hardly control.