• The Korean Journal of Applied Statistics
• /
• 제35권6호
• /
• pp.703-724
• /
• 2022

Although longitudinal studies mainly produce multivariate longitudinal data, most of existing statistical models analyze univariate longitudinal data and there is a limitation to explain complex correlations properly. Therefore, this paper describes various methods of modeling the covariance matrix to explain the complex correlations. Among them, modified Cholesky decomposition, modified Cholesky block decomposition, and hypersphere decomposition are reviewed. In this paper, we review these methods and analyze Korean children and youth panel (KCYP) data are analyzed using the Bayesian method. The KCYP data are multivariate longitudinal data that have response variables: School adaptation, academic achievement, and dependence on mobile phones. Assuming that the correlation structure and the innovation standard deviation structure are different, several models are compared. For the most suitable model, all explanatory variables are significant for school adaptation, and academic achievement and only household income appears as insignificant variables when cell phone dependence is a response variable.

• Nutrition Research and Practice
• /
• 제17권5호
• /
• pp.959-968
• /
• 2023

BACKGROUND/OBJECTIVES: Few studies have provided evidence of the association between diet quality and dental caries. This study aimed to examine the association between diet quality and untreated dental caries in a Korean representative population. SUBJECTS/METHODS: The study population included a sample of 13,815 participants, aged ≥ 19 from the Korea National Health and Nutrition Examination Survey during 2013-2015. The explanatory variable was diet quality and the outcome variable was untreated dental caries. Untreated dental caries were defined by the number of decayed teeth recorded according to the criteria established by the World Health Organization. Diet quality was defined by using the Korean Healthy Eating Index (KHEI) through the 24-h recall methods. We assessed the association between diet quality and untreated dental caries while adjusting for age, sex, education, income, smoking status, dental visits, toothbrushing frequencies, obesity, and diabetes mellitus. RESULTS: The mean overall KHEI scores in the untreated dental caries group were significantly lower than those in the group without untreated dental caries. Significant differences were observed in the untreated dental caries group based on the KHEI quartiles (P < 0.001). After adjusting for potential confounders, the quartiles of KHEI scores showed an association with untreated dental caries, demonstrating a dose-effect trend (odds ratio [OR], 1.57; 95% confidence interval [CI], 1.35-1.84 for 1st quartile; OR, 1.38; 95% CI, 1.19-1.59 for 2nd quartile; OR, 1.32; 95% CI, 1.14-1.53 for 3rd quartile; reference quartile highest]). CONCLUSIONS: The findings indicated an inverse association between diet quality and untreated dental caries in Korean adults. Healthcare providers should take into account the significant role of diet quality in preventing and managing oral health.

• Korean Journal of Hospice Care
• /
• 제7권2호
• /
• pp.15-25
• /
• 2007

The purpose of this study was to survey the hospital staff's perception of hospice and death and thereby, suggest the ways to help them have a mature attitude towards and a better understanding of death through an effective education on hospice. For this purpose, this study was designed to provide some data useful for the hospital staff not experienced in facing the dying patients to handle the desperate situation skillfully and engage themselves more effectively in their hospice services. For this study, the researcher conducted a questionnaire survey for the staff of 'C' hospital in Seoul about their hospice philosophy, attitudes towards hospice and perception of death for the period from February, 2006 to March, 2006. A total of 751 subjects responded effectively to the survey. The data collected were analyzed using the SF55 11.0 for ANOVA and T-test in order to test the relationships among subjects' perception of death, their demographic variables, their health condition, their hospice philosophy formed from their experiences of patients' death and hospice services and their attitudes towards hospice. Besides, the correlations among their hospice philosophy, perception of death and attitudes towards hospice were tested. The results of this study can be summarized as follows; First, as a result of testing the relationships among subjects' experiences of health consulting. their experiences of patients' death and hospice and their hospice philosophy, it was confirmed that their experiences of health and death consulting and their experiences of having been educated were relevant. Second, it was found that such variables as health condition, death, experience of hospice and attitude towards hospice were not significantly correlated with each other. Third, as a consequence of testing the relationships among health condition, death, experience of hospice and perception of death, it was disclosed that only the physical health condition was significant. Fourth, it was confirmed that subjects' hospice philosophy, perception of death and attitudes towards hospice were at the usual level on average. Fifth, hospice philosophy, perception of death and attitudes towards hospice were found correlated significantly with each other. Sixth, as a result of the stepwise variable adjustment for such variables as hospice philosophy, perception of death, attitudes towards hospice, it was found that the adjusted r-square value was 0.347 when departments, experience of having been requested by dying patient for consulting, experience of having been educated on hospice, religion and marital status were set as independent variables. And the estimated value of each variable was found significant. Seventh, as a consequence of conducting the multiple regression analysis by setting 'religion' as significant independent variable, it was found that the estimated value of physical health condition was not significant statistically. This, as a result of the simple regression analysis for 'religion' only, its explanatory power was found .197, while its adjusted r-square value was 0.20. Eight, it was found that subjects' attitude towards hospice was significantly correlated with such variables of experience of patient's or relative's death, experience of having been requested for consulting about death, gender, marital status and departments. As a result of the multiple regression analysis and the subsequent stepwise adjustment for this variable, it was found that only 'experience of having been requested for consulting' had some explanatory power: its adjusted r-square value was 0.089. As discussed above, this study tested the correlations among various variables including hospital staff's attitude towards hospice and perception of death and thereby, provided for the data useful for their education on hospice. This study may be significant in that it proved that it would be essential to educate hospital staff on hospice for more effective care of hospice patients and their family members at hospital.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• 제39권1호
• /
• pp.81-91
• /
• 2019

Although the number of users of urban railways is greatly influenced by the land use plan around the railway station, Korea has been studying this problem in a small scale, so that the entrance width is uniformly calculated irrespective of the land use plan, And there is little deviation. Therefore, this study aims to establish a demand estimation model for the entrance and exit of urban railway stations. For this purpose, the demand, land use area, and socioeconomic indicators for each of the 20 urban railway stations were surveyed at 200m and 500m Regression model. The model is based on the assumption that the dependent variable (response variable) of the model is set to 1 day, peak 1 hour, peak time 5 minutes, Education, and park) and socioeconomic indicators (population, employer, employee, and student) as independent variables (explanatory variables). As a result, it was analyzed that the fit of the model is more statistically significant when the use area of the land use by 500 meters of the center radius of the city rail is used as an independent variable and the demand for the daily use of the railway station is used as a dependent variable. The purpose of this study is to estimate the optimal size of urban railway entrance in order to improve the mobility of the user and the transportation weak in urban railway station.

• Management & Information Systems Review
• /
• 제31권1호
• /
• pp.89-116
• /
• 2012

This paper is an empirical study for the listed manufacturing companies in the Korea Stock Exchange during the sample period(2001-2010). The research is based on the target adjustment model(Shyam-Sunder and Myers(1999)) and the pecking order model(Frank and Goyal(2003)), and is aimed at reflecting the critical viewpoint of Chirinko and Singha(2000). An analysis in the model of Shyam-Sunder and Myers(1999) shows the value is too low to support the pecking order model in view of the following results. A target adjustment coefficient value is between 0 and 1, and is significant variable and explanatory power is very high, while deficit-in-funds coefficients close to 0. In addition, the result of an empirical test following the methodology used by Frank and Goyal(2003) does not support the pecking order theory.

• Industry Promotion Research
• /
• 제5권3호
• /
• pp.31-36
• /
• 2020

This study explores the determinants of capital structure of the hospitality industry such as hotels, lodging industry and tourism industry using financial data from 2000 to 2019. Several explanatory variables suggested by related theories and past studies were regressed with the dependent variable, debt ratio for the entire sample period, pre-crisis period and post-crisis period and the regression coefficients of the sales expenses, profitability and firm size were found to be statistically significantly negative. Especially the sign of the coefficient of the firm size was opposite to that of the manufacturing industry, which implies the uniqueness of the hospitality industry.

• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.969-980
• /
• 2017

Galloping is one of the most serious vibration problems in transmission lines. Power lines can be extensively damaged owing to aerodynamic instabilities caused by ice accretion. In this study, the accident probability induced by galloping phenomenon was analyzed using logistic regression analysis. As former studies have generally concluded, main factors considered were local weather factors and physical factors of power delivery systems. Since the number of transmission towers outnumbers the number of weather observatories, interpolation of weather factors, Kriging to be more specific, has been conducted in prior to forming galloping accident estimation model. Physical factors have been provided by Korea Electric Power Corporation, however because of the large number of explanatory variables, variable selection has been conducted, leaving total 11 variables. Before forming estimation model, with 84 provided galloping cases, 840 non-galloped cases were chosen out of 13 billion cases. Prediction model for accidents by galloping has been formed with logistic regression model and validated with 4-fold validation method, corresponding AUC value of ROC curve has been used to assess the discrimination level of estimation models. As the result, logistic regression analysis effectively discriminated the power lines that experienced galloping accidents from those that did not.

• Journal of the Korean Data and Information Science Society
• /
• 제20권6호
• /
• pp.1093-1101
• /
• 2009

Quantile regression has become a more widely used technique to describe the distribution of a response variable given a set of explanatory variables. This paper proposes a novel modelfor quantile regression using doubly penalized kernel machine with support vector machine iteratively reweighted least squares (SVM-IRWLS). To make inference about the shape of a population distribution, the widely popularregression, would be inadequate, if the distribution is not approximately Gaussian. We present a likelihood-based approach to the estimation of the regression quantiles that uses the asymmetric Laplace density.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• 제20권1호
• /
• pp.131-142
• /
• 2017

The function of urban parks as wildlife habitats is becoming increasingly important. The urban park serves as a key area for preserving urban biodiversity. The purpose of this study is to estimate the bird species diversity in 30 parks in Cheonan city and quantitatively analyze the influence of vegetation, park structure and landscape connectivity index. As the results, a total of 27 birds species and 1,509 individuals were found at the sites and the largest number of birds were found in the Cheongsa park with 17 species. The optimal regression model was selected as the explanatory variables for the logged park area (LPA), the tree cover ratio (Co_T) and the patch betweenness centrality (PB). LPA and Co_T mean the internal characteristics of the park, and PB was the external environmental variable meaning landscape connectivity. LPA was the most important factor (73.3%) as bird habitat, and the PB could be interpreted as a factor that should be considered as important (26.7%). It will be possible to consider these environmental variables in the park and green area construction and management.

• Journal of Nutrition and Health
• /
• 제28권7호
• /
• pp.644-652
• /
• 1995

The purpose of this study was to examine the relationship between sugar intake and behavioral problems in Korean school children. The subjects were 280 school children lived in Soung Nam city. Nutrient and sugar intakes were measured by 24-hour recall method and food frequency method through personal interview. Hyperactivity scores of children were measured by teacher and mother using conners Rating Scale-Revised. The average daily total sugar intake for the total sample was 63.0$\pm$37.4g(Range : 10g-220g). The result of stepwise multiple regression analysis using the sugar intake as dependent variable showed that energy, participation of school lunch program, Vit B2, protein, education of fathers, niacin, calcium are significant explanatory variables, explaining 44.8% of variation. As a result of the Conners scale test by teacher, 4% of children were Attention Deficit Hyperactivity Disorder(ADHD) children. A result of the Conners scale test by mother, 8% of children were ADHD children. The result of simple regression analysis had not shown significant relationship between sugar intake and ADHD scores. But the result of the Conners test by teacher, sugar intake(69.9$\pm$37.1g) of ADHD children were significantly higher than sugar intake(62.9$\pm$37.7g) of normal children(p<0.01).