Loading [MathJax]/jax/output/CommonHTML/jax.js
  • Title/Summary/Keyword: LOGISTIC REGRESSION ANALYSIS

Search Result 4,467, Processing Time 0.027 seconds

A Study on Ages, Learnings, Monthly Incomes and Occurrence of Dental Diseases among Industrial Workers in Korea (일부 남성 근로자들의 연령, 교육 수준 및 월 평균 수입과 구강병 발생양상에 관한 연구)

  • Kim, Mi-Jeong
    • Journal of dental hygiene science
    • /
    • v.2 no.2
    • /
    • pp.63-67
    • /
    • 2002
  • The purpose of this study was to develop more effective dental health education program and to reduce the occurrence of dental diseases among industrial men-workers in Korea. The questionaire and dental examination were given to 782 industrial men-workers who visited Asan Medical Center for the purpose of health examinations in 2000. The obtained results were as follows; 1. According to the results of logistic regression analysis, both ages (especially under 30's: P=0.027) and monthly incomes (especially under 1,000,000 won: P=0.000) show negative relationships with the occurrence of dental caries. 2. As the results of logistic regression analysis, ages shows positive relationship and monthly incomes shows negative relationship (only under 1,000,000 won: P=0.059) with the occurrence of missing teeth. 3. According to the results of logistic regression analysis of periodontal disease, the model shows no significance (P=0.117). 4. As the results of logistic regression analysis, both monthly incomes and ages show positive relationships with the occurrence of abrasion.

  • PDF

Comparison analysis of big data integration models (빅데이터 통합모형 비교분석)

  • Jung, Byung Ho;Lim, Dong Hoon
    • Journal of the Korean Data and Information Science Society
    • /
    • v.28 no.4
    • /
    • pp.755-768
    • /
    • 2017
  • As Big Data becomes the core of the fourth industrial revolution, big data-based processing and analysis capabilities are expected to influence the company's future competitiveness. Comparative studies of RHadoop and RHIPE that integrate R and Hadoop environment, have not been discussed by many researchers although RHadoop and RHIPE have been discussed separately. In this paper, we constructed big data platforms such as RHadoop and RHIPE applicable to large scale data and implemented the machine learning algorithms such as multiple regression and logistic regression based on MapReduce framework. We conducted a study on performance and scalability with those implementations for various sample sizes of actual data and simulated data. The experiments demonstrated that our RHadoop and RHIPE can scale well and efficiently process large data sets on commodity hardware. We showed RHIPE is faster than RHadoop in almost all the data generally.

Principal Components Logistic Regression based on Robust Estimation (로버스트추정에 바탕을 둔 주성분로지스틱회귀)

  • Kim, Bu-Yong;Kahng, Myung-Wook;Jang, Hea-Won
    • The Korean Journal of Applied Statistics
    • /
    • v.22 no.3
    • /
    • pp.531-539
    • /
    • 2009
  • Logistic regression is widely used as a datamining technique for the customer relationship management. The maximum likelihood estimator has highly inflated variance when multicollinearity exists among the regressors, and it is not robust against outliers. Thus we propose the robust principal components logistic regression to deal with both multicollinearity and outlier problem. A procedure is suggested for the selection of principal components, which is based on the condition index. When a condition index is larger than the cutoff value obtained from the model constructed on the basis of the conjoint analysis, the corresponding principal component is removed from the logistic model. In addition, we employ an algorithm for the robust estimation, which strives to dampen the effect of outliers by applying the appropriate weights and factors to the leverage points and vertical outliers identified by the V-mask type criterion. The Monte Carlo simulation results indicate that the proposed procedure yields higher rate of correct classification than the existing method.

Patterns and Determinats of Supplementary Educational Investment on Childern (자녀보충교육투자의 유형과 결정요인)

  • 주인숙
    • Journal of Family Resource Management and Policy Review
    • /
    • v.4 no.1
    • /
    • pp.1-13
    • /
    • 2000
  • This study examined patterns and determinants of families’supplementary educational investment on children. By supplementary educational investment, it meant the amounts of money spent on children’s education other than regular formal schooling expenses. The data used were from the 「1996 Household Expenditure Survey」conducted by the National Statistical Office. The statistical methods employed were descriptive statistics, cluster analysis and logistic multiple regression analysis. Results of cluster analysis revealed five different patterns of family supplementary education expense with relatively even proportion of families allocated to each pattern. The five education expenditure patterns were arts education dominant; other education dominant; gymnastics·clerical·computer education dominant; college entrance exam preparation dominant; and private tutoring dominant. Results of logistic regression analysis showed that the possibility of being in a pattern affected by various family socioeconomic variables. Important factors affecting there patterns were children’s schooling stage, residence, and mother’s education.

  • PDF

Multivariate Analysis for Clinicians (임상의를 위한 다변량 분석의 실제)

  • Oh, Joo Han;Chung, Seok Won
    • Clinics in Shoulder and Elbow
    • /
    • v.16 no.1
    • /
    • pp.63-72
    • /
    • 2013
  • In medical research, multivariate analysis, especially multiple regression analysis, is used to analyze the influence of multiple variables on the result. Multiple regression analysis should include variables in the model and the problem of multi-collinearity as there are many variables as well as the basic assumption of regression analysis. The multiple regression model is expressed as the coefficient of determination, R2 and the influence of independent variables on result as a regression coefficient, β. Multiple regression analysis can be divided into multiple linear regression analysis, multiple logistic regression analysis, and Cox regression analysis according to the type of dependent variables (continuous variable, categorical variable (binary logit), and state variable, respectively), and the influence of variables on the result is evaluated by regression coefficientβ, odds ratio, and hazard ratio, respectively. The knowledge of multivariate analysis enables clinicians to analyze the result accurately and to design the further research efficiently.

Accidents Model of Arterial Link Sections by Logistic Model (로지스틱모형을 이용한 가로구간 사고모형)

  • Park, Byung-Ho;Lim, Jin-Kang;Han, Su-San
    • Journal of the Korean Society of Safety
    • /
    • v.25 no.4
    • /
    • pp.90-95
    • /
    • 2010
  • This study deals with the accident model of arterial link section in Cheongju. The objective is to develop the accident model of arterial link section using the logistic regression. In pursuing the above, the study uses the 258 accident data occurred at the 322 arterial link section. The main results are as follows. First, Nagellerke R2 of developed accident model is analyzed to be 0.309 and t-values of variable that explains goodness of fit are evaluated to be significant. Second, the variables adopted in the model are AADT, the number of exit and entry. These variables are all analyzed to be statistically significant. Finally, the analysis of correct classification rate shows that the total accident of correct classification rate is analyzed to be 72.7% at the arterial link section.

Content Analysis of Main National Environmental Dispute Cases from Five Recent Years (최근 5년간 주요 중앙환경분쟁조정 사건의 내용 분석)

  • Park, Jeong-Ho;Yang, Sung-Bong
    • Journal of Environmental Science International
    • /
    • v.25 no.7
    • /
    • pp.989-998
    • /
    • 2016
  • In this study, we analyzed the content and compensation factors of 337 cases of national environmental disputes from five recent years (2000~2014). Causes of damage were noise-vibration in 234 cases (69%), sunlight in 48 cases (14%), air pollution in 19 cases (6%), water pollution in 15 cases (4%), odor in 13 cases (4%), and others factors in 8 cases (3%). Sources of damage were construction in 224 cases (66%), structures in 36 cases (11%), vehicle on road in 31 cases (9%), industry in 18 cases (5%), environmental facility in 11 cases (3%), livestock facility in 6 cases (2%), and other sources in 11 cases (3%). From the results of logistic regression analysis, important factors associated with compensation were found to be damage amount, damage distance, zoning districts, source, and administrative disposition.

Analysis of Landslide Hazard Area using RS/GIS (RS/GIS를 이용한 산사태 위험지역 분석)

  • Lee Yong-Jun;Park Geun-Ae;Kim Seong-Joon
    • Proceedings of the KSRS Conference
    • /
    • 2006.03a
    • /
    • pp.202-205
    • /
    • 2006
  • The objective of this study is to analyze the hazard-areas for landslide using GIS and RS. LRA (Logistic Regression Analysis) and AHP (Analytic Hierarchy Program) methods were used for evaluation of the hazard-areas by six topographic factors (slope, aspect, elevation, soil drain, soil depth, land use). These methods were applied to Anseong-si where frequent landslides were occurred mainly by the regional heavy rainfall. A landslide hazard-map of Anseong-si could describe into 7 hazard-grades. As results, LRA method was underestimated in higher grades areas, while AHP method was underestimated in lower grades areas. In order to evaluate the hazard-areas for landslides with accuracy, these results of each method were overlapped and the results of suggested method were compared with the historical landslide hazard records of KFRI (Korea Forest Research Institute).

  • PDF

Policy and Managerial Issues of Voice over Internet Protocol(VoIP) (인터넷전화의 정책 및 경영이슈측면에서의 이용자분석)

  • Kim, Ji-Hee;Sung, Yoon-Young;Kweon, O-Sang;Kim, Jin-Ki
    • Journal of Information Technology Applications and Management
    • /
    • v.14 no.4
    • /
    • pp.221-233
    • /
    • 2007
  • Which factors should influence consumer consideration to subscribe to Voice over Internet Protocol (VoIP)? Policy issues, managerial concerns, and demographic variables are possible factors. This paper discusses policy and managerial issues regarding VoIP adoption. A model that explains VoIP adoption is proposed and tested. This study analyzes a survey of 750 prospective VoIP users in Korea. The testing is accompanied by logistic regression and discriminant analysis. The results show that trust in VoIP, relative comparison of Quality to fixed service, numbering plan, satisfactions of call Quality and customer services on both fixed and mobile services have impacts on the adoption of VoIP. Implications for VoIP providers and policy makers are presented.

  • PDF

Financial Supports of Government for Nonprofit Social Service Organizations in the United States (비영리 조직에 대한 정부재정지원에 영향을 미치는 요인 : 미국의 사례를 중심으로)

  • Rho, Yeon-Hee
    • Korean Journal of Social Welfare
    • /
    • v.49
    • /
    • pp.129-161
    • /
    • 2002
  • This study explores whether there are differences in financial structure and governmental support between social service organizations and other nonprofit organizations. In addition, it analyzes what factors are related to governmental supports for both types of nonprofit organizations. Guided by the argument that specific areas where nonprofits primarily operate can explain a difference of relations between nonprofit organizations and funders, this study compares revenue sources and expenditures of social service organizations and other nonprofit organizations in the United States. Also, based on resource dependence theory and taking some important indexes from financial ratio analysis, this study also identifies factors that affect governmental supports for nonprofit organizations. The study sample consists of 10,690 organizations that reported tax form 990 in 1996. Binary logistic regression analysis was conducted for the study. The results show that social service organizations obtained more revenue from government than other nonprofit organizations. Also, logistic regression analysis suggests that revenue diversification and financial characteristics were significantly associated with governmental supports for nonprofit organizations in the United States.

  • PDF