• 제목/요약/키워드: multinomial logistic analysis

검색결과 155건 처리시간 0.023초

Can We Identify Trip Purpose from a Clickstream Data?

  • Choe, Yeongbae
    • Journal of Smart Tourism
    • /
    • 제2권2호
    • /
    • pp.15-19
    • /
    • 2022
  • Destination marketing organizations (DMOs) utilize the official website for marketing and promotional purposes, while tourists often navigate through the official website to gather necessary information for their upcoming trips. With the advancement of business analytics, DMOs may need to exploit the clickstream data generated through their official website to develop more suitable and persuasive strategic marketing and promotional activities. As such, the primary objective of the current study is to show whether clickstream data can successfully identify the trip purposes of a particular user. Using a latent class analysis and multinomial logistic regression, this study found the meaningful and statistically significant variations in webpage visits among different trip purpose groups (e.g., weekend getaways, day-trippers, and other purposes). The findings of this study would provide a foundation for more data-centric destination marketing and management practice.

노년기 기능장애의 이질적 발달궤적과 예측요인 (The Heterogeneous Trajectories of Functional Disability in Older Adults and Their Predictors)

  • 이현주
    • 한국노년학
    • /
    • 제37권1호
    • /
    • pp.15-32
    • /
    • 2017
  • 본 연구는 노년기 기능장애의 평균적인 변화가 아니라 하위집단에 따라 어떻게 다른 변화가 나타나는지 분석하고, 건강 및 사회적 특성의 변화가 기능장애 변화와 어떠한 관련을 갖는지 분석하였다. 분석 자료는 고령화연구패널조사(Korean Longitudinal Study of Ageing)의 1차 년도에서 4차 년도까지의 자료를 사용하였다. 기능장애의 이질적 발달궤적을 분석하기 위해 Latent Class Growth Analysis(LCGA)를 사용하였고, 잠재계층에 대한 건강 및 사회적 특성 변화의 영향력을 알아보기 위해 다항로지스틱 회귀분석(Multinomial logistic analysis)을 실시하였다. 연구 결과, 우리나라 65세 이상 지역사회 거주노인의 기능장애 변화에서 평균 변화궤적으로 설명될 수 없는 다양한 변화양상이 확인되었다. 전체 노인의 78%가 독립적 기능형으로 나타났고, 17.3%의 노인은 상당한 수준의 기능장애 변화를 경험하였다. 즉 4.4%는 높은 기능장애 지속형에, 7.1%는 급격한 증가형에, 5.5%는 완만한 증가형에, 그리고 4.7%는 중간-감소형에 속하였다. 또한 우울증상이나 인지기능이 악화되는 것과, 사회참여와 친한 사람과의 만남이 감소하는 것이 기능장애 증가를 높이는 주요 위험요인으로 나타났다. 지역사회 거주노인의 기능장애가 개인에 따라 다양한 양상으로 변화한다는 것을 실증적으로 분석한 본 연구 결과에 근거할 때, 노년기 기능장애를 보다 세분화하여 이해하는 것이 필요하며, 각 집단에 따른 특성을 고려한 차별적인 연구와 실천이 이루어져야 할 것이다.

A Study on the Clinical Features of Ordinary Sleeping Patterns Based on the Sasang Constitution, Using the Logistic Regression

  • Choi Jae-Young;Choi Jeong-Rak;Lee Yung-Seop;Park Seong-Sik
    • 대한한의학회지
    • /
    • 제25권4호
    • /
    • pp.171-179
    • /
    • 2004
  • Objective : This study was undertaken for discovering the characteristics of sleep in ordinary symptoms based on the Sasang Constitution. The result of this study could be helpful to understand and to identify patients such as Taeumin, Soyangin Soeumin or Taeyangin. Methods : There were 1,229 patients (529 men), who answered the questionnaire about their ordinary sleeping patterns. They were diagnosed, including their clinical Sasang Constitution, by the Sasang Constitution specialist at Bundang Oriental Hospital of Dongguk University. By applying the multinomial and binary logistic regression analysis to those collected materials, we can measure the characteristics and the influence of ordinary sleeping patterns to the dependent variable (Sasang Constitution). Results : In order of the item's influence that had decided one's constitution, between Taeumin and Soeumin, Taeumin snored frequently or well more than Soeumin, Soeumin had more dreams and more sleeping times than Taeumin, and Taeumin struggled frequently or well more than Soeumin. Between Soyangin and Soeumin, Soeumin dreams more frequently than Soyangin, Soyangin snored frequently or well more than Soeumin, and Soeumin has more sleeping times than Taeumin. Between Taeumin and Soyangin, Taeumin snored frequently or well more than Soyangin. Between Taeyangin and a group of the other constitutions, Taeyangin felt unwell after sleeping more than the other constitutions, the other constitutions awaked frequently more than Taeyangin during sleeping. Conclusion : This study will be used for identifying patients as Taeumin, Soyangin, Soeumin or Taeyangin by contrast with each other.

  • PDF

한우 수소 고기 관능평가 데이터에 대한 범주형 자료 분석 (Categorical data analysis of sensory evaluation data with Hanwoo bull beef)

  • 이혜정;조수현;김재희
    • Journal of the Korean Data and Information Science Society
    • /
    • 제20권5호
    • /
    • pp.819-827
    • /
    • 2009
  • 국립축산과학원에서 수집한 한우 관능 평가 데이터에 대해 사회 인구학적 요인과 한국 소비자들의 맛 평가에 대한 연관성을 연구하고자 한다. 소비자 거주지역, 연령, 성별, 직업, 월수입과 쇠고기 부위를 설명변수로 맛등급 평가를 반응변수로 이항 다중 로지스틱 모형과 다항 다중 로지스틱 모형을 적합하고 회귀계수별 유의성 검정과 적합도 검정을 실시하였다. 단계별 변수 선택으로 최종 모형을 선택하고 반응변수 범주에 대한 오즈비를 계산하여 관련성을 파악한다. 그 결과 거주 지역, 연령, 월수입과 쇠고기 부위 변수들이 선택되었다. 영남에서 맛을 비교적 높게 평가하는 경향이 있으며 수입이 많고 연령이 높을수록 맛을 까다롭게 평가하는 경향을 보인다. 쇠고기 부위별로는 우둔에 비해서 등심이 다른 부위들 중 맛에 대한 차이가 크다고 볼 수 있다.

  • PDF

학교수업에서 수학교사에 대한 인식의 잠재프로파일 분석 (A latent profile analysis of perceptions about Mathematics teachers in school lessons)

  • 고동현;정희선
    • 한국수학교육학회지시리즈A:수학교육
    • /
    • 제57권2호
    • /
    • pp.75-92
    • /
    • 2018
  • Based on Perceptions about Mathematics Teachers (PMT) perceived by high school students, measured by 2189 students from Seoul Educational Longitudinal Study 2014 (SELS 2014), latent profile analysis (LPA) identified five distinct types of student groups (positive, partial positive, middle, negative, extreme negative). These student of positive, middle, and negative groups are positive, moderate and negative perceptions about math teachers. Partial positive group generally had a positive perception about mathematics teachers, extremely negative group was very negative about mathematics teachers. Both of these groups had peculiarly inconsistent trends and several anomalies. The Multinomial logistic regression analyses also indicated that individual factors (gender, major, self-concept, resilience, self-assessment, career maturity), school factors (friendship, relationship with school teachers) and parental factors (academic-relationship, emotional-relationship) were significant predictors of PMT profile groups. The Analysis of variance also indicated that mathematics class (attitude, satisfaction and atmosphere), Mathematics achievement were significant predictors of PMT profile groups. The profiling of perceptions about mathematics teachers resulted in enhanced understanding of the complex range of processes students employed. During mathematics class, implementation of smooth interactions and communications between students and teachers added in the teaching and learning of mathematics.

Accuracy of periodontal probe visibility in the assessment of gingival thickness

  • Kim, Young-Sung;Park, Ji-Sun;Jang, Young-Hun;Son, Jung-Hun;Kim, Won-Kyung;Lee, Young-Kyoo;Kim, Su-Hwan
    • Journal of Periodontal and Implant Science
    • /
    • 제51권1호
    • /
    • pp.30-39
    • /
    • 2021
  • Purpose: The present study was undertaken to examine whether periodontal probe visibility (PV) accurately reflects gingival thickness (GT) and to identify factors affecting PV using cluster and multivariate analyses. Methods: The clinical characteristics of the maxillary central incisors (n=90 subjects) were examined. Clinical photographs, sex, PV, probing depth, gingival width, papilla height, GT as measured with an ultrasonic device, and the ratio of crown width to crown length were recorded. Multivariate analysis, using multinomial baseline-category logistic regression, was used to identify factors predictive of PV. Cluster analysis was used to identify gingival biotypes. Results: In the multivariate analysis, sex was the only significant predictor of PV (odds ratio, 6.48). Two clusters of subjects were created based on morphometric parameters. The mean GT among cluster A subjects was significantly lower than that among cluster B subjects (P=0.015). No significant difference was found between cluster A and B subjects in terms of PV score (P=0.583). Conclusions: Periodontal PV was not associated with GT as measured directly using an ultrasonic device. Sex was a highly significant predictor of periodontal PV. GT was found to be correlated with morphological characteristics of the periodontium.

사상체질별 비만요인에 대한 환자-대조군 연구 (A Case-Control Study on Risk Factors of Obese Patients of Each Sasang Constitution)

  • 이갑수;석재화;김상혁;김윤희;이의주;김달래;고병희;이수경
    • 사상체질의학회지
    • /
    • 제19권2호
    • /
    • pp.94-112
    • /
    • 2007
  • 1. Backgrounds and Aims Human being is divided into 4 constitution types(Taeyangin, Soyangin, Taeumin, and Soumin). According to Sasang Constitutional Medicine[SCM] Each constitution has its own incidence, treatment and prevention of disease. The purpose of this study is to find the relation of dietary habits, life styles and Psychosocial stress with obesity in each Sasang Constitution. 2. Methods 975 subjects who have received health examinations and diagnosis of Sasang Constitution at Kyung-hee Medical Center were divided into each constitutional group. Each constitutional group was then divided into obese group and normal group. We evaluated risk factors of obesity such as dietary habits, life styles, and Psychosocial stress. These data were statistically analysed to investigate the relations between risk factors and obesity. And then significant factors were analysed by multinomial logistic regression analysis to get each odds ratio. 3. Results In a multinomial logistic regression analysis adjusted for age and sex, promotion of appetite and overeating or excessive diet elevated risks of obesity in Taeumin, promotion of appetite and high speed of diet elevated risks of obesity in Soyangin, and Psychosocial stress elevated risks of obesity in Soeumin. 4. Conclusions The results suggest that promotion of appetite and overeating or excessive diet may be major risk factors for obesity in Taeumin, promotion of appetite and high speed of diet in Soyangin and Psychosocial stress and dyschezia in Soeumin.

  • PDF

Risk Factors for the Severity of Complications in Minimally Invasive Total Gastrectomy for Gastric Cancer: a Retrospective Cohort Study

  • Roh, Chul Kyu;Lee, Soomin;Son, Sang-Yong;Hur, Hoon;Han, Sang-Uk
    • Journal of Gastric Cancer
    • /
    • 제21권4호
    • /
    • pp.352-367
    • /
    • 2021
  • Purpose: Minimally invasive gastrectomy is a promising surgical method with well-known benefits, including reduced postoperative complications. However, for total gastrectomy of gastric cancers, this approach does not significantly reduce the risk of complications. Therefore, we aimed to evaluate the incidence and risk factors for the severity of complications associated with minimally invasive total gastrectomy for gastric cancer. Materials and Methods: The study included 392 consecutive patients with gastric cancer who underwent either laparoscopic or robotic total gastrectomy between 2011 and 2019. Clinicopathological and operative characteristics were assessed to determine the features related to postoperative complications after minimally invasive total gastrectomy. Binomial and multinomial logistic regression models were used to identify the risk factors for overall complications and mild and severe complications, respectively. Results: Of 103 (26.3%) patients experiencing complications, 66 (16.8%) and 37 (9.4%) developed mild and severe complications, respectively. On multivariate multinomial regression analysis, independent predictors of severe complications included obesity (OR, 2.56; 95% CI, 1.02-6.43; P=0.046), advanced stage (OR, 2.90; 95% CI, 1.13-7.43; P=0.026), and more intraoperative bleeding (OR, 1.04; 95% CI, 1.02-1.06; P=0.001). Operation time was the only independent risk factor for mild complications (OR, 1.06; 95% CI, 1.001-1.13; P=0.047). Conclusions: The risk factors for mild and severe complications were associated with surgery, indicating surgical difficulty. Surgeons should be aware of these potential risks that are related to the severity of complications so as to reduce surgery-related complications after minimally invasive total gastrectomy for gastric cancer.

교통사고 데이터의 패턴 분석과 Hybrid Model을 이용한 피해자 상해 심각도 예측 (Pattern Analysis of Traffic Accident data and Prediction of Victim Injury Severity Using Hybrid Model)

  • 주영지;홍택은;신주현
    • 스마트미디어저널
    • /
    • 제5권4호
    • /
    • pp.75-82
    • /
    • 2016
  • 우리나라의 경제 성장과 도로 환경의 변화를 통해 국내 자동차 시장이 성장하였으나, 이로 인해 교통사고율 또한 증가하였고, 인명 피해가 심각한 수준이다. 이에 따라, 정부에서는 교통사고 데이터를 개방하고 문제를 해결하기 위한 정책을 수립 및 추진 중이다. 본 논문에서는 교통사고 데이터를 이용하여 클래스의 불균형을 해소하고, Hybrid Model 구축을 통한 교통사고 예측을 위해 원본 교통사고 데이터와 Sampling을 수행한 데이터를 학습 데이터로 사용한다. 두 학습데이터에 연관규칙 학습기법인 FP-Growth 알고리즘을 이용하여 교통사고 상해 심각도와 연관된 패턴을 학습한다. 두 학습 데이터의 연관 패턴을 분석을 통해 같은 연관된 패턴을 추출하고 의사결정트리와 다항 로지스틱 회귀분석기법에 연관된 속성에 가중치를 부여하여 융합형 Hybrid Model을 구축하고 교통사고 피해자 상해 심각도를 예측하는 방법에 대해 제안한다.

미취학 자녀를 둔 기혼 취업여성의 시간사용 유형에 관한 연구 (Typology of Time Use of Married Working Women with the Preschool Child(ren) in Korea)

  • 이선명;여정성
    • Human Ecology Research
    • /
    • 제54권5호
    • /
    • pp.541-550
    • /
    • 2016
  • This study explored a typology (or time allocation), investigated personal and work characteristic differences among time allocation types, and identified determinants of time allocation types of married working women with a preschool child. The data source for this research was the 2014 Time Use Survey conducted by Statistics Korea. We analyzed 368 time diaries (184 for weekdays and 184 for weekends) using frequency, mean, cluster analysis, chisquare, analysis of variance (ANOVA), Duncan's test, and multinomial logistic analysis. The results of this research are as follows. Time allocation of married working women with a preschool child was classified into three different types of 'work-centered,' 'work-family balanced,' and 'family-centered.' The work-centered type accounted for 14.7% of total respondents, and compared with other types, this type of people spent more time working, and less time doing house-work, caring for family, and having leisure. The work-family balanced type represents more than half of the total, and spend more time working on weekdays and house-working, having leisure on weekends. The family-centered type represents 28.8%, and spends most of the time doing house-work and caring for family on both weekdays and weekends. Occupation, employment status, monthly income, and weekly hours of work were different for each type. Occupation, employment status, perception of lack of time, health condition, and weekly hours of work were identified as determinants for each type.