• The Korean Journal of Applied Statistics
• /
• v.30 no.4
• /
• pp.539-553
• /
• 2017

We propose a multi-state model to analyze semi-competing risks data with interval-censored or missing intermediate events. This model is an extension of the three states of the illness-death model: healthy, disease, and dead. The 'diseased' state can be considered as the intermediate event. Two more states are added into the illness-death model to incorporate the missing events, which are caused by a loss of follow-up before the end of a study. One of them is a state of the lost-to-follow-up (LTF), and the other is an unobservable state that represents an intermediate event experienced after the occurrence of LTF. Given covariates, we employ the Lin and Ying additive hazards model with log-normal frailty and construct a conditional likelihood to estimate transition intensities between states in the multi-state model. A marginalization of the full likelihood is completed using adaptive importance sampling, and the optimal solution of the regression parameters is achieved through an iterative quasi-Newton algorithm. Simulation studies are performed to investigate the finite-sample performance of the proposed estimation method in terms of empirical coverage probability of true regression parameters. Our proposed method is also illustrated with a dataset adapted from Helmer et al. (2001).

• The Korean Journal of Applied Statistics
• /
• v.33 no.1
• /
• pp.25-46
• /
• 2020

This paper presents ordinal probit semiparametric regression models using Bayesian Spectral Analysis Regression (BSAR) method. Ordinal probit regression is a way of modeling ordinal responses - usually more than two categories - by connecting the probability of falling into each category explained by a combination of available covariates using a probit (an inverse function of normal cumulative distribution function) link. The Bayesian probit model facilitates posterior sampling by bringing a latent variable following normal distribution, therefore, the responses are categorized by the cut-off points according to values of latent variables. In this paper, we extend the latent variable approach to a semiparametric model for the Bayesian ordinal probit regression with nonparametric functions using a spectral representation of Gaussian processes based BSAR method. The latent variable is decomposed into a parametric component and a nonparametric component with or without a shape constraint for modeling ordinal responses and predicting outcomes more flexibly. We illustrate the proposed methods with simulation studies in comparison with existing methods and real data analysis applied to a Korean National Health and Nutrition Examination Survey (KNHANES) 2016 for investigating nonparametric relationship between smoking behavior and coffee intake.

• Journal of agricultural medicine and community health
• /
• v.40 no.2
• /
• pp.80-92
• /
• 2015

Objectives: To clarify the association between dust from large construction sites and allergic and respiratory conditions among residents in Sejong city. Methods: We included 379 individuals older than 50 years from three areas of Sejong city; two areas near construction sites and one area for a comparison. Prevalence of self-reported allergic and respiratory conditions was compared across the three areas using logistic regression to adjust for covariates including age, gender, smoking, and educational attainment. A total of 16 individuals were interviewed to take details of the residents' experiences of construction work. Results: Those living in the nearby areas around construction sites were generally found to have the increased prevalence for all allergic and respiratory conditions. Odds Ratio(OR)s for cough and sneezing among the six symptoms and allergic rhinitis among the three diagnosed diseases reached statistical significance but only OR for cough remained significant after adjustment: adjusted OR for cough was 2.63 (95% CI, 1.07-6.46). Two relevant themes emerged from semi-structured interview were; 1) most residents from the affected area reported a considerable level of exposure to construction dust, 2) about half of them noted that construction dust influences allergic- and respiratory health. Conclusions: General pattern provides suggestive evidence that living close to construction sites may be positively associated with elevated risks of allergic and respiratory conditions. Efforts should be made to establish preventive measures and a comprehensive in-depth health impact assessment on this issue.

• Journal of Gastric Cancer
• /
• v.17 no.2
• /
• pp.132-144
• /
• 2017

Purpose: To identify baseline prognostic factors for survival in patients with disease progression, during or after chemotherapy for the treatment of advanced gastric or gastroesophageal junction (GEJ) cancer. Materials and Methods: We pooled data from patients randomized between 2009 and 2012 in 2 phase III, global double-blind studies of ramucirumab for the treatment of advanced gastric or GEJ adenocarcinoma following disease progression on first-line platinum- and/or fluoropyrimidine-containing therapy (REGARD and RAINBOW). Forty-one key baseline clinical and laboratory factors common in both studies were examined. Model building started with covariate screening using univariate Cox models (significance level=0.05). A stepwise multivariable Cox model identified the final prognostic factors (entry+exit significance level=0.01). Cox models were stratified by treatment and geographic region. The process was repeated to identify baseline prognostic quality of life (QoL) parameters. Results: Of 1,020 randomized patients, 953 (93%) patients without any missing covariates were included in the analysis. We identified 12 independent prognostic factors of poor survival: 1) peritoneal metastases; 2) Eastern Cooperative Oncology Group (ECOG) performance score 1; 3) the presence of a primary tumor; 4) time to progression since prior therapy <6 months; 5) poor/unknown tumor differentiation; abnormally low blood levels of 6) albumin, 7) sodium, and/or 8) lymphocytes; and abnormally high blood levels of 9) neutrophils, 10) aspartate aminotransferase (AST), 11) alkaline phosphatase (ALP), and/or 12) lactate dehydrogenase (LDH). Factors were used to devise a 4-tier prognostic index (median overall survival [OS] by risk [months]: high=3.4, moderate=6.4, medium=9.9, and low=14.5; Harrell's C-index=0.66; 95% confidence interval [CI], 0.64-0.68). Addition of QoL to the model identified patient-reported appetite loss as an independent prognostic factor. Conclusions: The identified prognostic factors and the reported prognostic index may help clinical decision-making, patient stratification, and planning of future clinical studies.

• Korean Journal of Community Nutrition
• /
• v.24 no.6
• /
• pp.465-475
• /
• 2019

Objectives: This study investigated dietary and lifestyle factors associated with the weight status among Korean adolescents in multicultural families. Methods: This cross-sectional study analyzed 1,751 multicultural families' adolescents who participated in the 2017-2018 Korea Youth Risk Behavior Surveys. Information on dietary and lifestyle factors was self-reported using a web-based questionnaire and this information included breakfast and foods consumption, perceived health status, alcohol drinking, smoking, physical activity, and weight control efforts. Body mass index (BMI) was calculated based on the self-reported height and body weight (kg/㎡). Weight status was assessed according to the 2017 Korean National Growth Chart: underweight (weight-for-age <5^th percentiles), overweight (85^th≤ BMI-for-age <95^th percentiles), and obese (BMI-for-age ≥95^th percentiles). Multiple logistic regression analysis was performed to examine the dietary and lifestyle factors associated with weight status after adjustment for covariates. Results: Among Korean adolescents from multicultural families, the prevalence of overweight/obesity was 20.9%, whereas about 7% of adolescents were underweight. The weight status did not show differences according to gender, school level, area of residence, and household income. Compared to adolescents who did not have breakfast during the previous week, those who had breakfast 3-4 days/week and ≥5 days/week had a 42% (p=0.021) and a 37% (p=0.009) lower prevalence of overweight/obesity, respectively. The adolescents who frequently consumed carbonated soft drinks (≥5 times/week) showed an odds ratio (OR) of 1.69 (95% CI=1.01-2.83) for overweight/obesity relative to those adolescents who did not consume carbonated soft drinks. The OR of being underweight for adolescents who ate fast food ≥3 times/week was 1.97 (95% CI=1.04-3.71) compared to those adolescents who had not eaten fast food during the previous week. Conclusions: Dietary and lifestyle factors were associated with overweight/obesity as well as underweight among Korean adolescents in multicultural families. Our findings could be used to design and provide nutrition interventions for this specific population.

• Journal of Society of Preventive Korean Medicine
• /
• v.12 no.2
• /
• pp.61-72
• /
• 2008

Objectives : The aim of this study was to evaluate effects of herbal medicine and other associated factors for abnormal liver function tests(especially total bilirubin, AST, ALT, and ${\gamma}$GT) levels in outpatients at an oriental medical clinic. Methods : A cross-sectional study based on clinical records was conducted on 504 patients at one Oriental medical clinic in Seoul, Korea. They were tested a liver function tests for screening and 497 patients ranging from the age of 4 to 74 were chosen for the study. Patients with basal liver disease or DM were excluded during the screening process. Patients were classified into case(abnormal) and control(normal) groups by normal liver function test references. Results and Conclusions : In this study, Significant correlations for abnormal total bilirubin levels was age, for abnormal AST was gender, for abnormal ALT were gender, smoking, marriage status, and job, for abnormal ${\gamma}$GT were age, gender, obesity, alcohol, smoking, marriage status, and job using the Chi-square test(p<0.05). There was no significant correlations for abnormal LFTs by using herbal medication history, and intake duration. After controlling other covariates, logistic regression analysis showed that the significant associated factors for abnormal total bilirubin levels were age(odds ratio[OR]=0.87, 95% confidence intervals [CI]=0.87-0.99). For abnormal AST levels was obesity(OR=2.45, CI=1.2-4.9), for abnormal ALT levels were age(OR=1.01, CI=0.99-1.03), male gender(OR=3.31, CI=1.62-6.76), and obesity(OR=3.71 CI=2.28-6.08). For abnormal ${\gamma}$GT levels were male gender(OR=4.83 CI=1.34-17.43), obesity(OR=3.29, CI=1.74-6.22), alcohol (OR=2.51, CI=1.19-5.28), and smoking(OR=2.29, CI=1.16-4.50). Herbal medication history was not as a risk factor for all abnormal liver function tests. Therefore, people who are male, obese, alcohol drinker and smoker will have higher liver function test levels. But intake of herbal medication or the duration of intake may not be the risk factor for abnormal liver function test results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.227-236
• /
• 2016

This study tested the effects of stress on smartphone addiction via depression and self-efficacy among college students, and the analysis results were as follows: setting mediator and extra variables significantly correlated with the criterion variable as covariates and applying the regression analysis and SPSS Macro as well as bootstrapping method, to verify the mediating effects of depression and self-efficacy in stress and smartphone addiction. This study analyzed the direct effects of stress on the depression, self-efficacy, and smartphone addiction of college students and found that stress had direct effects on their depression and self-efficacy and also indirect effects on their smartphone addiction via depression and self-efficacy. Both depression and self-efficacy had dual and partial mediating effects on the influences of stress on their smartphone addiction. Stress had significant dual mediating effects on their smartphone addiction via the indirect paths of depression and self-efficacy, and high stress also had significant direct effects on their smartphone addiction, thus validating the dual mediation model. These findings demonstrate the need to develop programs to mitigate the stress and depression of college students and enhance their self-efficacy in order to reduce their smartphone addiction.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.201-215
• /
• 1993

The health status of workers in a foundry was analyzed in a study which consisted of evaluations of respiratory health together with environmental measurements. The results from environmental measurements showed values exceeding permissible exposure limits. A t-test was done with log transformed and untransformed data to examine the statistical significance for the noncompliance with exposure standards. For the analysis of categorical health outcomes, $\chi$-square test with 2 $\times$ 2 tables and logistic regression analysis were employed. For continuous variables, multiple linear regression was done against assessed risk factors. Pros and cons of different parameters in the compliance (or noncompliance) testing were presented. Respiratory function did not show any relation with occupational exposures, which may be due to the healthy worker effects. Strategies for controlling time dependent covariates were discussed in relation to the healthy worker effect. The scope of statistical analysis in occupational health studies is still limited in Korea without a suitable external comparison group such as credible vital statistics for the whole nation. Internal comparisons between different exposure status often result in unstable estimates of effect, and proportional morbidity study is discussed as an alternative potential research tool.

• Journal of Preventive Medicine and Public Health
• /
• v.43 no.3
• /
• pp.235-244
• /
• 2010

Objectives: To examine the prophylactic antibiotic use in reducing surgical site infection. Methods: This was a retrospective study for patients aged 18 years and older who underwent gastrectomy, cholecystectomy, colectomy, cesarean section and hysterectomy. The data source was quality assessment data of the Health Insurance Review & Assessment Service gathered from medical records of 302 national hospitals. Prophylactic antibiotic use was defined as: timely antibiotic administration or inappropriate antibiotic selection. We performed hierarchical logistic regression to examine the association between prophylactic antibiotic use and surgical site infection with adjustment for covariates. Results: The study population consisted of 16 348 patients (1588 gastrectomies, 2327 cholecystectomies, 1,384 colectomies, 3977 hysterectomies and 7072 cesarean sections) and surgical site infection was identified in 351 (2.1%) patients. The rates of timely antibiotic administration and inappropriate antibiotic selection varied according to procedures. Cholecystectomy patients who received timely prophylactic antibiotic had a significantly reduced risk of surgical site infection compared with those who did not receive a timely prophylactic antibiotics (OR 0.64, 95% CI=0.50-0.83), but no significant reduction was observed for other procedures. When inappropriate prophylactic antibiotics were given, the risk of surgical site infection significantly increased: 8.26-fold (95% CI=4.34-15.7) for gastrectomy, 4.73-fold (95% CI=2.09-10.7) for colectomy, 2.34-fold (95% CI=1.14-4.80) for cesarean section, 4.03-fold (95% CI=1.93-8.42) for hysterectomy. Conclusions: This study examines the association among timely antibiotic administration, inappropriate antibiotic selection and surgical site infection. Patients who received timely and appropriate antibiotics had a decreased risk of surgical site infection. Efforts to improve the timing of antibiotic administration and use of appropriate antibiotic are needed to lower the risk of surgical site infection.

• Journal of the Korean Society of Child Welfare
• /
• no.56
• /
• pp.221-251
• /
• 2016

The purpose of this study was to examine whether single-parent family status affects children's school adjustment through children's self-care and media exposure. In addition, the study investigated the mediating effects of self-protection and media exposure of children by analyzing whether single-parent family status has effects on school adjustment through self-care and media exposure of children. For this purpose, we used data of 1,916 students in the 4th grade who participated in the 4th year of the Korean Children and Youth Panel Survey (KCYPS). The results of the structural equation modeling showed that single-parent family environment not only had direct effects on the school adjustment, but also had effects on school adjustment through self-care of children. In addition, it was revealed that self-care of children influenced school adjustment through media exposure. One of the covariates, monthly income of households, did not affect the level of children's self-care. This result draws attention to the problems of the structural deficit of single-parent families. Therefore, political measures that correspond to the structural characteristics and special needs of single-parent families, along with their current financial support, are needed to improve the level of school adjustment of children from single-parent families.