• Title/Summary/Keyword: multinomial logistic analysis

Search Result 150, Processing Time 0.025 seconds

Drinking Patterns Among Korean Adults: Results of the 2009 Korean Community Health Survey

  • Ryu, So Yeon;Crespi, Catherine M.;Maxwell, Annette E.
    • Journal of Preventive Medicine and Public Health
    • /
    • v.46 no.4
    • /
    • pp.183-191
    • /
    • 2013
  • Objectives: In Korea, the proportion of deaths due to alcohol is estimated at 8.9%, far exceeding the global estimate of 3.8%. Therefore, this study was performed to examine the factors associated with low-risk, moderate-risk, and high-risk drinking patterns in Korean adults and to identify target populations for prevention and control of alcohol-related diseases and deaths. Methods: We analyzed data from 230 715 Korean adults aged 19 years and older who participated in the 2009 Korean Community Health Survey. Multinomial logistic regression analysis was used to examine associations between socio-demographic and health-related factors and patterns of alcohol use. Results: A substantially larger proportion of men than women engaged in high risk (21.2% vs. 3.4%) and moderate-risk alcohol use (15.5% vs. 8.2%). In both sexes, moderate- and high-risk uses were associated with younger age, higher income, being currently employed, smoking, being overweight/obese, and good self-rated health. Conclusions: Given the large proportion of the population that is engaging in moderate- and high-risk drinking and given the social norms that support this behavior, public health policies and campaigns to reduce alcohol consumption targeting the entire population are indicated.

A Comparative Study on the Accuracy of Important Statistical Prediction Techniques for Marketing Data (마케팅 데이터를 대상으로 중요 통계 예측 기법의 정확성에 대한 비교 연구)

  • Cho, Min-Ho
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.14 no.4
    • /
    • pp.775-780
    • /
    • 2019
  • Techniques for predicting the future can be categorized into statistics-based and deep-run-based techniques. Among them, statistic-based techniques are widely used because simple and highly accurate. However, working-level officials have difficulty using many analytical techniques correctly. In this study, we compared the accuracy of prediction by applying multinomial logistic regression, decision tree, random forest, support vector machine, and Bayesian inference to marketing related data. The same marketing data was used, and analysis was conducted by using R. The prediction results of various techniques reflecting the data characteristics of the marketing field will be a good reference for practitioners.

Personal Remittances: An Empirical Study in Oman

  • UDDIN, Mohammed Ahmar;ALAM, Md. Shabbir
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.8 no.3
    • /
    • pp.917-929
    • /
    • 2021
  • This study highlights the importance of remittance, the factors which affect the percentage of income remitted, and the investment options available to reduce remittance. For the year 2019, the remittances from Oman totaled $9.1 billion. Oman was among the top remitters with remittance to gross domestic product (GDP) ratio of 11.9%. A survey was conducted on 300 resident expats in Oman. The descriptive analysis shows that the maximum remittance percentage is between 21%-40% of income. The multinomial logistic regression results show that outward remittance depends on gender, age, occupation, number of dependent in Oman, and the number of dependent in the home country. Regarding investment, the most preferred investment option is business, followed by real estate and financial services. Age and education are found to affect investment options. This paper tries to fill the literature gap, especially for the case of Oman, by exploring what determines the level of remittance and the preferred choices for retaining funds. This study adds to the existing literature, as no previous study is available regarding how personal factors can influence the level of remittance and investment in a small oil-exporting developing country like Oman. The study will be helpful to policymakers and academicians in devising policies to retain and invest the outwards remittances in Oman.

Mobilizing Informal Economic Sector to Uphold Urban Institutional Resilience: A Case Study of Rawalpindi, Pakistan

  • RIAZ, Tayyaba;WAHEED, Abdul;ALVI, Shahzad
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.9 no.5
    • /
    • pp.397-407
    • /
    • 2022
  • The informal economy is a large part of the urban economy. The informal economy accounts for about half of Pakistan's GDP. This research examined nine different areas of Rawalpindi's Central Business District's business sector (CBD). A survey of 404 respondents from 16 CBD marketplaces enables a comprehensive examination of who works in the informal and formal economic sectors, how much they earn, their goals, perception of their job, and their degree of similarity to the rest of the working population. Furthermore, the statistics illustrate the pro-cyclical connections between the informal economic sector and the formal economy. The Multinomial Logistic Regression (MLR) technique is used for the analysis. The MLR results indicated the informal economic sector holds positive relation with earning members in a family, business expertise, average business sale, and negative relation with education level, satisfaction with government tax policies, household expense, and average investment in the business. From a resilience standpoint, governance is considered an intentional collective action to preserve a stable system condition. Hence, the current study recommends tax reforms and government institution reorganization to mobilize the informal sector and make effective institutional governance.

Impact of litter on femur and tibial morphology, bone biomechanics, and leg health parameters in broiler chickens

  • Komal Khan;Mehmet Kaya;Evrim Dereli Fidan;Figen Sevil Kilimci
    • Animal Bioscience
    • /
    • v.36 no.9
    • /
    • pp.1393-1402
    • /
    • 2023
  • Objective: In this study effects of three types of beddings on broiler leg health and bone biomechanics were evaluated. Methods: A total of 504 male chicks (Ross 308) were randomly placed on three beddings (4 replicates/group; 42 birds/pen), zeolite-added litter (ZL), plastic-grid flooring (PF), and wood shavings (WS). On day 42, chickens were weighed, slaughtered, and samples (bone, muscle, and drumstick) were collected. Bones were subjected to leg health tests, morphometric measurements, biomechanical testing, and ash analysis. Results: Broilers in PF and WS groups showed higher live weight than the ZL group (p<0.001), and the incidence of tibial dyschondroplasia (TD) and varus valgus deformity due to distal bending was significantly higher in PF (p<0.001). Multinomial logistic regression showed that bedding has a significant (p = 0.038) contribution toward the development of TD. Tibial strength (p = 0.040), drumstick width (p = 0.001), and total femur and epiphyseal ash contents (p = 0.044, 0.016) were higher in the ZL group. Chicken live weight was correlated with tibial length and weight (r = 0.762, 0.725). Conclusion: Flooring and the type of bedding material directly affect broiler bone length, strength and leg health. Plastic bedding improves the slaughter weight of chickens on the expense of leg deformities, and zeolite litter improves leg health and bone strength.

The Effect of Cognition Degree of Green Life on Green Consumer Behavior (녹색생활관련 인지정도가 녹색소비행동에 미치는 영향 연구)

  • Jung, Joo-Won;Cho, So-Yeon
    • Journal of Environmental Science International
    • /
    • v.23 no.8
    • /
    • pp.1455-1462
    • /
    • 2014
  • The purpose of this study is to examine green consumer behavior (green product purchasing behavior and green consumption life) affected by demographical characteristics, and cognition degree of green life (cognition of a green indicator, a green life catalyst system, and environmental problems). It's also to promote strategy and suggest effective activation plans for the vitalization of green consumer behavior. To carry out the task, verification of credibility, multiple regression analysis, two-step cluster analysis, and multinomial logistic analysis were used. The results are as follows: First, the factors that effect green product purchasing behavior were gender, age, cognitive of a green indicator, carbon points system, electricity peak hour system, and seriousness of environmental damage due to lifestyle. Second, the factors that effect green lifestyle were gender, age, carbon grade indicator system, cognition of a green system, and the seriousness of environmental damage due to lifestyle. Third, the comparative group characteristic analysis showed low rates for careless green consumer behavior groups compared to the passive green consumer behavior groups in cognition of a green indicator, green system, and environmental problems. For active green consumer behavior groups, the analysis showed high rates in cognition of carbon grades, eco-labeling, electricity peak hour system, and environmental damage due to lifestyle. In order to encourage green consumer behavior, it's evident that cognition of a green indicator, a green life catalyst system, and environmental problems need to be improved through strategic education and continuous encouragement.

Analysis of Student's Satisfaction Types of the Campus-Life and Affecting Factors using Latent Profile Analysis (잠재프로파일 분석을 이용한 대학생활 만족유형 분류 및 영향요인 분석)

  • Ryu, HoJun;Kil, HyeJi;Rah, Min-Joo
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.8
    • /
    • pp.482-491
    • /
    • 2022
  • The purpose of this study was to classify latent profiles based on satisfaction of student by the campus-life&educational-experiences and to identify factors affecting satisfaction according to each type. For this study, data from the survey of the A univ(1,952 data) were used. To analyze this, a latent profiles analysis was applied to identify subgroups, in which the students by the campus-life&educational-experiences satisfaction, and a multinomial logistic regression model was applied to verify factors affecting group classification. As a result of the analysis, first four groups were classified in the order of 'average·class·highest·relationship satisfaction type'. Second the factors affecting the classification into the remaining three types with 'the average satisfaction type' as a reference group were found to be significant influencing factors(gender, grade, admission process, GPA grade). Based on these results, this study suggested implications for planning and promoting student-tailored education and student support policies at the university level.

Influence of Limerence and Ruminative Response on Dating Violence in Romantic Relationship (연인관계에서의 집착과 반추적 반응이 데이트 폭력에 미치는 영향)

  • Jeong, Goo-Churl
    • The Journal of the Korea Contents Association
    • /
    • v.17 no.11
    • /
    • pp.479-490
    • /
    • 2017
  • The study analyzed the relationship between dating violence and limerence and ruminative response in romentic relationship. The subjects were 205 college students who had experience of dating. And mean age of subjects was 22.1 years. Analysis methods were correlation analysis, ANOVA, two-step cluster analysis, and multinomial logistic regression analysis. The results of this study are as follows. First, self-reproach ruminative respone were significantly higher the victim group and perpetrator victim group than the general group. Second, all sub-factors of ruminative respone were significantly higher the victim group and perpetrator victim group than the general group. Third, the self-reproach ruminative respone was significant positive explanatory variable on dating violence. Fifth, the victim limerence experience significantly increased the odds ratio of victim group of dating violence by 3.3 times, and that of perpetrator victim group of dating violence by 10.9 times. Based on these findings, he discussed the importance of dating violence and the importance of limerence and rumination.

A Study on the Validity and Reliability of the Eight-Constitution Questionnaire (8체질(體質) 설문지(說問紙)의 타당도(妥當度), 신뢰도(信賴度)에 관한 연구(硏究))

  • Min, Jae-Young;Kim, Min-Yong;Park, Young-Jae;Park, Young-Bae
    • The Journal of the Society of Korean Medicine Diagnostics
    • /
    • v.11 no.2
    • /
    • pp.27-44
    • /
    • 2007
  • Background: Eight-Constitution Medicine (ECM) classifies the human body into eight constitutions. Diagnosis of discrimination of the eight constitutions depends on a unique pulse diagnosis. However, pulse diagnosis is subjective and requires vigorous training. Objectives: This study aims to analyze the validity and reliability of the Eight-Constitution Questionnaire as a diagnostic method. Methods: Participants of this study were outpatients in six ECM clinics located in Seoul. The resources were collected from 409 patients who were classified into one of the eightconstitutions according to their pulse types and their responses to constitution-acupuncture therapy. SPSS 13.0 for Windows was used for statistical analysis: factor analysis, reliability analysis, independent sample t-test, and multinomial logistic regression were used to verify the results. Results and Conclusions: 1. The proportion of participants' constitutions is in the order of Pancreotonia (23.7%), Colonotonia (19.8%), Pulmotonia (18.1%), Hepatonia (16.9%), Vesicotonia (8.1%), Cholecystotonia (7.3%), Renotonia (5.3%) and Gastrotonia (0.7%). 2. Sevencomponents and 74 items were selected through factor factor and relaibility analysis performed on about 251 items. 3. The firstcomponent's mean is significantly higher in Pancreotonia than that in other constitutions (p<0.05). The second is in Pulmotonia and Colonotonia, whereas the third is in Hepatonia and Cholecystotonia. Fifth is in Vesicotonia, the sixth is in Colonotonia, and the fourth and seventh are not significant in specific constitutions. 4. The percentage that Pancreotonia is correctly predicted is 96.9%, Pulmotonia is 91.9%, Colonotonia is 91.4%, Hepatonia is 88.4%, Vesicotonia is 81.8%, Gastrotonia is 66.7%, Renotonia is 66.7%, Choleeystotonia is 30.0%, and the total percentage is 85.3%.

  • PDF

A Study on the Consumption Patterns of Poor Households (빈곤계층의 소비패턴에 관한 연구 : 2007년과 2008년의 변화 비교)

  • Joung, Won Oh;Lee, Sun Jeong
    • Korean Journal of Social Welfare Studies
    • /
    • v.42 no.1
    • /
    • pp.305-331
    • /
    • 2011
  • This study analyzes the consumption patterns of the poor households. The first objective of this analysis is to show that the group living in poverty get not one consumption pattern but several types of consumption patterns. The second objective is to understand what factors effect the consumption patterns. This study use the data of Korea Welfare Panel Study in 2008 & 2009. In oder to achieve first goal, We conduct factor analysis and cluster analysis. And to achieve second goal, We conduct multinomial logistic Analysis. Major findings are as follows. First we find six patterns of consuming types of the poor households. They are education oriented consuming type, diet oriented type, social network oriented type, transportation-communication oriented type, health & medical oriented type, and housing expenditure oriented type. Second we find these consumption patterns are effected by not economic factors but socio-populational factors, especially by life cycle of members of household.