• 아동학회지
• /
• 제38권2호
• /
• pp.165-176
• /
• 2017

Objective: Delinquent peers are important predictors of adolescent delinquent behavior. Few studies have classified individuals into groups based on patterns of delinquent behavior among youth and their peers. This study identified latent groups based on adolescent-peer delinquency and examined psychosocial characteristics of each latent group. Methods: First, the study employed latent class analysis based on a nationally representative data of South Korean middle school students (N = 2,277). Both adolescent and peer delinquent behaviors comprised 13 items in the questionnaire that was self-reported by adolescents. Second, the study used multivariate regression models to analyze psychosocial symptoms of latent groups and conducted Wald tests to compare differences among latent groups. Results: Patterns of adolescent-peer delinquency were classified into six latent groups. "Mutual total delinquent group (1.2%)" showed high rates in most delinquent experiences. "Mutual status delinquent group (5.7%)" mainly experienced status delinquency, "Mutual violence delinquent group (5.3%)" showed high rates of violent delinquency. "Peer-only total high delinquent group (3.8%)" reported friends to have engaged in all types of delinquency and "Peer-only total medium delinquent group (11.8%)" reported peer involvement in multiple status and few violent delinquency. Finally, "low risk group (72.2%)" reported low rates of delinquency for themselves and their friends. Regression analysis showed that every "mutual" delinquent group presented significantly worse psychosocial problems than the "low risk group." Conclusion: Using person centered latent class analysis, this study classified six latent classes while considering both delinquent agents and various types of delinquency and investigated specific groups with greater risk of psychosocial problems.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.393-402
• /
• 2013

The Mahalanobis-Taguchi System (MTS) is a diagnostic and predictive method for multivariate data. In the MTS, the Mahalanobis space (MS) of reference group is obtained using the standardized variables of normal data. The Mahalanobis space can be used for multi-class classification. Once this MS is established, the useful set of variables is identified to assist in the model analysis or diagnosis using orthogonal arrays and signal-to-noise ratios. And other several techniques have already been used for classification, such as linear discriminant analysis and logistic regression, decision trees, neural networks, etc. The goal of this case study is to compare the ability of the Mahalanobis-Taguchi System and logistic regression using a data set.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.913-915
• /
• 1995

In this paper, a transient signal classification system using logistic regression and neural networks is presented, where four neural networks such as MLP, MLP-Class, RBF and LVQ are utilized to classify given transient signals, based on the logistic regression method. Also, some test results with experimental transient signal data are provided.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2002년도 봄 학술발표회 논문집
• /
• pp.274-283
• /
• 2002

This paper presents an efficient models for reinforeced concrete structures using CART-ANFIS(classification and regression tree-adaptive neuro fuzzy inference system). a fuzzy decision tree parttitions the input space of a data set into mutually exclusive regions, each of which is assigned a label, a value, or an action to characterize its data points. Fuzzy decision trees used for classification problems are often called fuzzy classification trees, and each terminal node contains a label that indicates the predicted class of a given feature vector. In the same vein, decision trees used for regression problems are often called fuzzy regression trees, and the terminal node labels may be constants or equations that specify the Predicted output value of a given input vector. Note that CART can select relevant inputs and do tree partitioning of the input space, while ANFIS refines the regression and makes it everywhere continuous and smooth. Thus it can be seen that CART and ANFIS are complementary and their combination constitutes a solid approach to fuzzy modeling.

• 보건의료산업학회지
• /
• 제11권3호
• /
• pp.115-127
• /
• 2017

Objectives : To determine the relationship between of subjective recognition of social class and mental health. Method: The participants were adults with mental health experience over the age of 20 from the Korea Health Panel in 2013 (n=5,126). Methods : Data were analyzed using SPSS Statistics 22.0 The chi-square test and logistic regression analysis used to verify the relationship between subjective recognition of social class and mental health. Results : Lower subjective recognition of social class was associated with experience of depression and suicidal ideation. Other factors associated with depression experience were subjective health status, gender, age, marital status, type of medical care, disability, subjective health status, current smoking and frequency of drinking. Experience of suicidal ideation was, by contrast, associated with subjective health status, age, marital status, economic activity, private insurance, subjective health status and frequency of drinking. Conclusions : Health policies and institutions must be established to optimize health and preventive medicine approaches, especially or mental health as well as the provision of services.

• 응용통계연구
• /
• 제26권4호
• /
• pp.661-674
• /
• 2013

본 논문에서는 S 대학교 2012년 1학기 수강신청 자료를 이용하여 학생들의 수강신청 행태를 분석하였다. 학생과 과목의 링크로 이루어진 2-모드 네트워크 자료를 학생과 학생의 링크로 이루어진 1-모드 네트워크 자료로 변환하였다. 학생들의 수강신청 행태를 자세히 살펴보기 위해 전체 네크워크를 단과대학별로 컴포넌트나 커뮤니티 같은 하위 네크워크로 세분한 후 중심성 지표 값을 통해 하위 네트워크의 특징을 설명하였다. 또한 다중 회귀분석모형을 써서 성별, 학년, 중심성 지표가 학점에 미치는 영향을 살펴보았다.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권7호
• /
• pp.543-553
• /
• 2020

The purpose of this study is to analyze the effects of subjective class consciousness on life satisfaction. This research aimed to not only analyze the relative explanatory power, but also the influence of satisfaction of life within the socioeconomic status where the elderly consider themselves to be an integral part. The elderly's satisfaction in life was analyzed in comparison with demographic characteristics such as gender and age. The correlations of objective socioeconomic characteristics such as income level and education level were also observed. For this purpose, the Korea Labor Panel 17th data (2014) was used to conduct a one-way batch distribution analysis and a hierarchical regression analysis. It was seen that there was a correlation in the Korean elderly in terms of class consciousness and life satisfaction. The elderly with a lower subjective class consciousness showed lower life satisfaction. The relative influences were stronger than the demographic and socioeconomic characteristics of the elderly, and the explanatory power was much higher than the objective income levels. These results show that the subjective perception of their socioeconomic status has a significant influence on the level of life satisfaction of the Korean elderly, independent of the objective income level.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권4호
• /
• pp.1371-1376
• /
• 2012

Background: Economic status is known to be directly or indirectly related to cancer incidence since it affects accessibility to health-related social resources, preventive medical checkups, and lifestyle. This study investigates the relationship between cancer incidence and family income in Korea. Methods:Using the Korean National Health Insurance cancer registration data in 2009, the relationship between their family income class and cancer risk was analyzed. The age-standardized incidence rates of the major cancers were calculated for men and women separately. After adjusting for age, residential area, and number of family members, cancer risks for major cancers according to family income class were estimated using a logistic regression model. Results: In men, the risk of stomach cancer for Income Class 5 (lowest) was 1.12 times (95% CI 1.02-1.23) higher than that of Income Class 1 (highest), for lung cancer 1.61 times (95% CI 1.43-1.81) higher, for liver cancer 1.22 times (95% CI 1.08-1.37) higher, and for rectal cancer 1.37 times higher (95% CI 1.18-1.59). In women, the risk of stomach cancer for Income Class 5 was 1.22 times higher (95% CI 1.08-1.37) than that for Income Class 1, while for cervical cancer it was 2.47 times higher (95% CI 2.08-2.94). In contrast, in men, Income Class 1 showed a higher risk of thyroid cancer and prostate cancer than that of Income Class 5, while, in women the same was the case for thyroid cancer. Conclusions: The results show the relationship between family income and cancer risk differs according to type of cancer.

• 디지털융복합연구
• /
• 제14권9호
• /
• pp.579-588
• /
• 2016

본 연구는 교양체육수업의 재미요인, 수업만족과 운동지속행동의 관계를 규명하고자 하였다. 이를 위해 경기도에 속한 4개 대학 학생을 대상으로 300부의 설문지를 회수하여 연구 자료로 사용이 가능한 275부를 분석에 사용하였다. 분석을 위해 통계프로그램은 PASW 18.0 프로그램을 이용하여 각 요인에 대한 기술통계를 제시하였으며 요인추출 및 문항 내적 일관성 확인을 위해 탐색적 요인분석중 주성분분석과 베리맥스 회전 방식을 선택하였다. 신뢰도 분석에는 크론바 알파를 통해 신뢰도를 확인하였다. 교양체육수업의 재미요인, 수업만족과 운동지속행동 요인에 대해서는 다중회귀분석을 실시하여 관계를 규명하고자 하였으며, 다음과 같은 결론을 얻었다. 첫째, 교양체육수업의 재미요인 중 교수행동, 체육성적, 체육환경, 운동능력, 운동지속행동에 유의한 영향력을 주는 것으로 나타났다. 둘째, 교양체육수업의 수업만족 중 운동지속행동에 영향을 주는 것은 교수행동, 체육성적 요인이 유의한 영향력을 주는 것으로 나타났다.

• 실천공학교육논문지
• /
• 제14권2호
• /
• pp.333-339
• /
• 2022

본 연구는 공과대학 학생들이 온라인 학습을 진행하였을 때 노트 필기를 병행하며 학습을 하는 경우에 대해 학습 효과 및 만족도, 집중력에 미치는 영향에 대해 연구하였다. 온라인 학습에서 학습 도구로 사용하기 위한 양식으로 코넬노트를 사용하였다. 설문 조사 결과, 학생들은 온라인 학습에서의 노트 필기가 수업 참여의 성실성, 적극성, 집중력에 도움이 되는 것으로 파악되었다. 통계 분석 결과, 노트 필기 제출 횟수와 학업성취도와의 양의 상관관계를 확인하였으며 단일/다중 회귀분석을 통해서 노트 필기 제출 횟수와 학업 성취도가 통계적으로 유의미함을 확인하였다. 다중 회귀 분석 결과, 평균적으로 학생들의 노트 필기 제출 횟수가 1회 증가할 경우, 이는 중간고사 점수 0.253점, 기말고사 점수 0.287점 상승에 통계적으로 유의미한 것을 확인하였다. 부트스트래핑 회귀분석을 실시한 결과에서도 필기노트 제출 횟수가 성적과도 유의미한 결과를 얻어 단일/다중회귀 분석의 결과가 적정함을 확인하였다. 온라인 상에서 강의를 수강하며 노트를 필기하고 온라인 제출함으로써 온라인 수업에서 학습의 질을 높일 수 있는 수업 전략이 될 수 있음을 확인하였다.