• 한국경영과학회지
• /
• 제41권1호
• /
• pp.127-143
• /
• 2016

This study applied DEA analysis to measure the relative efficiency of 35 companies that produce automobile body components. First, the input and output, the improvement target value of the calculated variables, and the reference group for benchmarking for inefficient groups to become efficient groups were established through DEA analysis. In addition, whether inefficiency was due to technical inefficiency or size was analyzed in connection with the cases of the actual companies through the measurement of scale efficiency. Second, a route for efficiency improvement was derived through DEA-Tier analysis by defining the possible group for benchmarking in actuality within the production industry of automobile body components where the primary cooperative company belonged. Third, the financial variables that generate the difference between efficient and inefficient groups were derived through logistic regression analysis. Financial strategies that determine the direction the indices should be improved to allow the inefficient group to become an efficient one were recommended. This research is expected to provide diagnostic methods for management efficiency and the direction of improvement to enhance the management efficiency of automotive parts makers by identifying the causes of the inefficiency of domestic automotive parts makers empirically. The study also provides financial strategies together with the target values of efficiency improvement for each individual company.

• Journal of Preventive Medicine and Public Health
• /
• 제15권1호
• /
• pp.179-186
• /
• 1982

The methods controlling the confounding factors were discussed using the data of secondary infertility with induced abortion. Mantel-Haenszel method and logistic model were applied in the analysis to find out which factors were confounding and/or effect modification variables. In the logistic analysis, the main effect of induced abortion, spontaneous abortion, age and interaction effect between induced abortion and spontaneous abortion were chosen as independent variables being regressed into logistic functions. Spontaneons abortion was interpreted as a potential confounder and at the same time potential effect modifier and age was interpreted as potential confounder. Spontaneous abortion was shown to be more important influencing factor than age to the secondary infertility. In the course of logistic analysis, the problem of parameter estimation and hypothesis testing, assessing the fitness of a model, and selection of the best model were briefly explained. For the program of logistic model, FUNCAT Procedure of SAS package was chosen.

• 한국산림과학회지
• /
• 제107권4호
• /
• pp.478-485
• /
• 2018

본 연구에서는 백두대간 등산로 훼손에 영향을 미치는 자연환경요인을 선정하고 영향 관계를 분석하였다. 연구대상지는 백두대간 고루포기산~생계령 구간 내 표본지 총 123개소이며 등산로 훼손, 임상, 하층식생, 수관밀도와 FGIS를 통해 얻은 경사, 토성, 암석노출 총 7가지 정보를 분석에 활용하였다. 등산로 훼손 발생지 43곳과 미발생지 80곳을 로지스틱 회귀분석을 통해 분석한 결과, 등산로 훼손에 영향을 미치는 자연환경요인으로 경사도, 하층식생, 토성, 암석노출 총 4가지를 선정하였다. 경사도와 하층식생은 양의 상관관계를 보였고 암석노출은 음의 상관관계로 나타났다. 토성은 미사 비율이 낮고 모래 비율이 높은 토성일수록 양의 상관관계를 보이는 것으로 나타났다. 따라서 등산로 훼손을 줄이기 위해서는 경사도, 하층식생, 토성, 암석노출 4가지 자연환경요인들을 적절하게 관리하여야 한다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.133-141
• /
• 2023

Approximately 40,000 elevators are installed every year in Korea, and they are used as a convenient means of transportation in daily life. However, the continuous increase in elevators has a social problem of increased safety accidents behind the functional aspect of convenience. There is an emerging need to induce preemptive and active elevator safety management by elevator management entities by strengthening the management of poorly managed elevators. Therefore, this study examines domestic research cases related to the evaluation items of the elevator safety quality rating system conducted in previous studies, and develops a statistical model that can examine the effect of elevator maintenance quality as a result of the safety management of the elevator management entity. We review two types: odds ratio analysis and logistic regression analysis models.

• Communications for Statistical Applications and Methods
• /
• 제11권2호
• /
• pp.275-285
• /
• 2004

We explore classification analysis using graphical methods such as sliced inverse regression and sliced average variance estimation based on dimension reduction. Some useful information about classification analysis are obtained by sliced inverse regression and sliced average variance estimation through dimension reduction. Two examples are illustrated, and classification rates by sliced inverse regression and sliced average variance estimation are compared with those by discriminant analysis and logistic regression.

• Annals of Occupational and Environmental Medicine
• /
• 제34권
• /
• pp.34.1-34.13
• /
• 2022

Background: This study aimed to investigate the association between lead exposure and serum gamma-glutamyl transpeptidase (γGT) levels as an oxidative stress marker in male steelworkers. Methods: Data were collected during the annual health examination of workers in 2020. A total of 1,654 steelworkers were selected, and the variables for adjustment included the workers' general characteristics, lifestyle, and occupational characteristics. The association between the blood lead level (BLL) and serum γGT level was investigated by multiple linear and logistic regression analyses. The BLL and serum γGT values that were transformed into natural logarithms were used in multiple linear regression analysis, and the tertile of BLL was used in logistic regression analysis. Results: The geometric mean of the participants' BLLs and serum γGT level was 1.36 ㎍/dL and 27.72 IU/L, respectively. Their BLLs differed depending on age, body mass index (BMI), smoking status, drinking status, shift work, and working period, while their serum γGT levels differed depending on age, BMI, smoking status, drinking status, physical activity, and working period. In multiple linear regression analysis, the difference in models 1, 2, and 3 was significant, obtaining 0.326, 0.176, and 0.172 (all: p < 0.001), respectively. In the multiple linear regression analysis stratified according to drinking status, BMI, and age, BLLs were positively associated with serum γGT levels. Regarding the logistic regression analysis, the odds ratio of the third BLL tertile in models 1, 2, and 3 (for having an elevated serum γGT level within the first tertile reference) was 2.74, 1.83, and 1.81, respectively. Conclusions: BLL was positively associated with serum γGT levels in male steelworkers even at low lead concentrations (< 5 ㎍/dL).

• 한국응급구조학회지
• /
• 제17권3호
• /
• pp.169-179
• /
• 2013

Purpose: The performance rate to perform Cardiopulmonary Resuscitation (CPR) by witness in out-of-hospital Cardiac Arrest (OHCA) is very low in South Korea. To prevent the death caused by OHCA, it is important to encourage the witness to perform CPR actively. The purpose of the study is to investigate the influencing factors to affect bystander CPR rate. Methods: I conducted a questionnaire survey from 25 February to 4 March, 2013, receiving responses from 517 people in Korea. The questionnaire included social demographic factors, history of heart disease, knowledge of CPR, and the reliability of emergency medical service (EMS). A logistic regression analysis was conducted. Results: Among the 517 respondents, 294 (57.4%) had intention of performing CPR. Multiple logistic regression analysis found the following significant predictors of CPR intention: gender (odds ratio [OR] = 0.390), age (OR = 1.024), religion (OR = 0.843), and knowledge of CPR (OR = 4.734). Conclusion: This study indicated that the strongest predictor is knowledge of CPR. Therefore, it would be helpful to teach CPR nationwide to encourage performing CPR. In addition, effect of CPR education in religious facilities is necessary.

• 한국농공학회논문집
• /
• 제49권3호
• /
• pp.63-68
• /
• 2007

The LRA(Logistic Regression Analysis) conducts a quantitative analysis by collecting a lot of samples and the AHP(Analytic Hierarchy Program) makes use of expert decision influenced by subjective judgment to a certain degree. This study is to suggest a combination method in mapping landslide hazard by giving equal weight for the result of LRA and AHP. Topographic factors(slope, aspect, elevation), soil dram, soil depth and land use were adopted to classify landslide hazard areas. The three methods(LRA, AHP, the combined approach) was applied to a $520km^2$ region located in the middle of South Korea which have occurred 39 landslides during 1999 and 2003. The suggested method showed 58.9% matching rate for the real landslide sites comparing with the classified areas of high-risk landslide While LRA and AHP Showed 46.1% and 48.7% matching rates respectively. Further studies are recommended to find the optimal combining weight of LRA and AHP with more landslide data.

• 한국학교보건학회지
• /
• 제35권3호
• /
• pp.133-142
• /
• 2022

Purpose: The purpose of the study was to investigate the effect of the environment on adolescent binge drinking. Methods: The study was designed as a cross-sectional study. Using statistics from the 17th (20201) Korea Youth Risk Behavior Web-based Survey, the raw data target population was 2,629,588 people, and the sample group used for analysis as the final data was 54,848 people. A Rao-scott 𝑥² test and univariate multinomial logistic regression analysis were performed using IBM SPSS 27.0. Results: In the results of univariate logistic regression analysis and multivariate logistic regression analysis, common related variables were gender, school level, academic achievement, sleep satisfaction, current smoking, daily smoking, and alcohol education experience. Conclusion: As a result of confirming the factors influencing binge drinking in Korean adolescents, some variables that increase the possibility of problematic drinking behavior in the socio-environmental areas such as individuals, communities, and national policies were identified. For effective prevention and intervention, it is necessary to develop programs to build a healthy environmental support system with support from national policies, including individuals, peer groups, and communities.

• 한국콘텐츠학회논문지
• /
• 제6권12호
• /
• pp.80-88
• /
• 2006

객체지향 패러다임에서 객체의 속성, 동작, 객체사이의 관계를 표현하는 클래스의 구성요소들에 대한 연관관계를 측정하는 응집도는 다양하게 연구되어 왔다. 리팩토링 분야에서도 개발자의 경험이나 직감에 의한 수동분석에서 자동분석에 이르기까지 다양한 연구가 제안되어 왔다. 리팩토링을 자동으로 수행하기 위해서는 수행여부를 결정짓는 객관적 판단기준에 대한 검증이 필요하다. 본 논문에서는 참조관계를 고려한 여섯 개의 메소드 위치 결정 요인과 메소드 위치에 대한 관계를 분석하기 위한 방법으로 로지스틱 회귀분석과 신경망을 사용할 것을 제안하였다. 실험 결과, 로지스틱 회귀 분석은 97%, 신경망은 90% 이상의 예측율을 보였으며, 로지스틱 회귀분석이 신경망을 이용한 방법보다 더 우수한 예측결과를 보였다. 또한 두 방법 모두 90% 이상의 예측율로 여섯 개의 메소드 위치 결정 요인이 리팩토링 무브 메소드의 객관적 판단기준으로 적용될 수 있음을 보였다.