• Communications for Statistical Applications and Methods
• /
• 제30권1호
• /
• pp.1-19
• /
• 2023

Observational data with missing or incomplete data are common in biomedical research. Multiple imputation is an effective approach to handle missing data with the ability to decrease bias while increasing statistical power and efficiency. In recent years propensity score (PS) matching has been increasingly used in observational studies to estimate treatment effect as it can reduce confounding due to measured baseline covariates. In this paper, we describe in detail approaches to competing risk analysis in the setting of incomplete observational data when using PS matching. First, we used multiple imputation to impute several missing variables simultaneously, then conducted propensity-score matching to match statin-exposed patients with those unexposed. Afterwards, we assessed the effect of statin exposure on the risk of heart failure-related hospitalizations or emergency visits by estimating both relative and absolute effects. Collectively, we provided a general methodological framework to assess treatment effect in incomplete observational data. In addition, we presented a practical approach to produce overall cumulative incidence function (CIF) based on estimates from multiple imputed and PS-matched samples.

• 대한치과의사협회지
• /
• 제55권2호
• /
• pp.116-127
• /
• 2017

Objectives : The aim of this study was to evaluate the cumulative survival rates of the implants placed into grafted sinus and determine the effect of age, gender, smoking, and systemic disease on the implant cumulative survival rates. Materials and Methods : The retrospective study was performed on 51 implants placed in 26 patients by one dentist at the Dental Implant Center, Seoul National University Dental Hospital in the years 2000-2010. The cumulative survival rates were calculated by the Kaplan-Meier method. The differences within the factors were analyzed using log-rank test and the correlations between the factors and implant survival rates were analyzed using Cox proportional hazard model. Results : 1. Among the total of 51 implants placed in 26 patients, 7 implants failed and 44 implants remained stable. The 1-year, 5-year, and 10-year cumulative survival rates were 92%, 88%, and 85%, respectively. 2. Patients in their 50s and in their 70s showed statistically significant difference in the cumulative survival rates (P < 0.05). Gender and the existence of systemic disease did not show significant results. 3. In the implant treatment, smokers showed 7.5 times higher risk of implant failure than non-smokers (P < 0.05). Conclusion: Implants installed in combination with sinus elevation can be considered as a reliable treatment method.

• The Journal of Advanced Prosthodontics
• /
• 제9권3호
• /
• pp.195-199
• /
• 2017

PURPOSE. The objective of this study was to determine the cumulative survival rate (CSR) and associated risk factors of Implantium implants by retrospective clinical study. MATERIALS AND METHODS. Patients who received Implantium implants (Dentium Co., Seoul, Korea) at Korea University Guro Hospital from 2004 to 2011 were included. The period between the first surgery and the last hospital visit until December 2015 was set as the observation period for this study. Clinical and radiographic data were collected from patient records, including all complications observed during the follow-up period. Kaplan-Meier analysis was performed to examine CSR. Multiple Cox proportional hazard model was employed to assess the associations between potential risk factors and CSR. RESULTS. A total of 370 implants were placed in 121 patients (mean age, 56.1 years; range, 19 to 75 years). Of the 370 implants, 13 failed, including 7 implants that were lost before loading. The 10-year cumulative survival rate of implants was 94.8%. The multiple Cox proportional hazard model revealed that significant risk factor of implant failure were smoking and maxillary implant (P<.05). CONCLUSION. The 10-year CSR of Implantium implants was 94.8%. Risk factors of implant failure were smoking and maxillary implant.

• 가정과삶의질연구
• /
• 제22권2호
• /
• pp.23-35
• /
• 2004

The purpose of this study is to evaluate child - care effects on young child's aggression in ecological context. For this, main effects, interaction effects and cumulative effects between child care experiences(quantity, quality, age of entry and stability) and maternal behavior as well as characteristics of child(sex, age and temperament) were examined. A total of 62 young children(34 boys and 28 girls) enrolled in child - care center were observed, and mothers and caregivers completed questionnaires. Data was analysed by three - way ANOVA, logistic regression and crosstabs. As result, first, main effects of quantity, rejective and regulative mothering on children's aggression were found. Second, there were significant interaction effects between both quality and quantity of day-care and rejective mothering. In particular, the interaction effects provided evidence that high - quality child - care served a compensatory function for extensive care and rejective mothering. Third, logistic regression analysis revealed risk factors for child's aggression and the effects of these risk factors were cumulative. Interaction effects of day-care quality and cumulative effects of day-care, characteristics of child and maternal behavior on child aggression were discussed.

• 환경영향평가
• /
• 제30권6호
• /
• pp.413-424
• /
• 2021

현행 환경영향평가 내 건강영향평가는 단일 물질별 기준초과 여부를 평가하고 적정 저감방안을 수립하도록 시행된다. 이에 따라 일부 개발 대상사업의 경우, 위해성평가의 모든 물질이 기준을 만족하지만 노출농도가 기준에 매우 근사한 경우가 존재한다. 하지만 여기서 모든 물질들의 동시 노출을 고려한다면 건강영향은 단일 물질별 관리보다 상당히 크게 발생할 여지가 있다. 실제로 수용체에 노출되는 건강영향을 파악하기 위해 배출물질의 통합평가 방법론의 구체화 및 개선방안 마련이 필요하다. 본 논문은 해외 선진사례 및 국내외 문헌고찰을 통해 누적위해성평가 및 위해성의 통합기법에 대한 개념을 정의하고, 산업단지 개발 시 다물질에 대한 건강영향을 고려한 누적위해성평가 활용을 위한 방법론을 제안하였다. 제안된 방법론을 통해 산업단지에 배출되는 유해중금속 4종(Ni, Cr⁶⁺, Cd, As)에 대한 통합지표를 산출하였으며, 과거 10년(2011~2020년) 간 수행된 산업단지 개발사업에 대한 사례적용을 통해 활용성을 확보하였다.

• 한국지역지리학회지
• /
• 제20권4호
• /
• pp.444-453
• /
• 2014

환경위험의 피해가 환경불평등과 사회불평등의 상호작용으로 인해 환경약자가 더 많이 피해를 받게 되는 환경 피해 불평등이 심화될 것으로 전망되고 있다. 본 연구는 서울시를 대상으로 미국 캘리포니아 환경보호청에서 개발한 환경보건 스크리닝 툴을 적용하여 통합적인 지역 규모의 누적영향을 평가하였다. 환경보건 취약지역을 스크리닝하기 위하여 환경노출과 건강영향의 환경부담, 민감집단과 사회경제적 요인의 인구특성에 따라 10개 지표를 선정하였다. 환경보건 스크리닝 툴을 통하여 2009~2011년 서울시 누적영향평가를 실시한 결과, 서울의 강서와 강남지역에서 위험요인이 높게 나타났며 강서지역은 환경부담과 인구특성 모두에서 위험요인이 높았고, 강남지역은 환경부담요인이 높은 것으로 나타났다. 연구결과는 민감 취약계층 등 환경약자를 고려한, 공정하고 효율적인 환경정책을 추진하기 위한 과학적인 근거를 제공할 수 있다.

• East Asian mathematical journal
• /
• 제36권1호
• /
• pp.55-60
• /
• 2020

We study a probabilistic approach for valuing an exchange option with default risk. The structural model of Klein [6] is used for modeling default risk. Under the structural model, we derive the closed-form pricing formula of the exchange option with default risk. Specifically, we provide the pricing formula of the option with the bivariate normal cumulative function via a change of measure technique and a multidimensional Girsanov's theorem.

• 한국항해항만학회지
• /
• 제36권10호
• /
• pp.795-801
• /
• 2012

본 논문에서는 요트 계류장과 같은 소형 해상 부유체의 위기수준을 모니터링하기 위한 확률 기반 위기평가기법(Probability based risk Evaluation Techniques, PET)의 이론적인 접근 방법을 기술하였다. PET는 5단계 척도의 위기 기준을 이용한 위기 판단 절차가 핵심 개념이다. 이러한 5단계 척도들은 폐형 공식을 이용한 해상 부유체 운동의 응답함수에 대한 누적확률분포에서 계산했다. 그리고 위기기준을 갖는 PET의 위기판단 절차를 제안하였다. PET의 유용성 검증을 위하여 시뮬레이션 실험을 하였는데, 실험에는 해상 부유체의 운동 측정에 사용할 ADIS16405 센서의 전기특성을 갖는 모의 신호를 이용하였다. 실험결과, PET의 위기평가 오차는 최대 5.0 수준에서 0.38 수준으로 나타났다. 이 결과로부터 제안한 PET가 모니터링 기법으로 사용 가능함을 확인하였다.

• 한국산업보건학회지
• /
• 제11권1호
• /
• pp.56-69
• /
• 2001

Objectives : This study was designed to develop and standardize a checklist for ergonomic risk factors, and to provide ergonomic guidelines for managing cumulative trauma disorders (CTDs) in automobile assembly lines. Methods : The Checklist for Ergonomic Risk Factors (CERF-1) was developed based on the results of previous studies, and then modified after performing pilot study. Information on the symptoms possibly related with CTDs was obtained using a self-reported Questionnaire from 465 automobile assembly workers. Their job conditions were examined to assess risk factors through both direct observation and video analysis. Results : Rate of detecting risky job through CERF-1 was 85.6%, and was similar to that (88.8%) by Occupational Safety and Health Adminstration(OSHA) checklist but higher than that (63.7%) by American National Standards Institute(ANSI) Z-365. Relationship of the exposure scores derived from CERF-1 with levels of symptom was greater (r=0.49) than OSHA (r=0.28) and ANSI Z-365 (r=0.22). Considering the relationship, jobs scoring higher than 16 could be classified as the Risk Job. and lower than 16 as the Low Risk Job. Sensitivity and specificity of the Risk Job were 92.5 % and 31.5 %, respectively. Odds ratio (OR) after age adjustment was 5.69 (95 % confidence interval 3.15-10.29) for the Risk Job, and these ORs were significantly different from those of the Low Risk Job. The exposure scores were Quite valid, in that the scores at the main survey were significantly correlated with those at the follow-up survey, as suggested by test-retest(r=0.88) and inter-rater reliability(r=0.80). Conclusions : The CERF-1, developed in this study, will be an efficient tool for evaluation of risk jobs for CTDs in automobile assembly lines, and can be used easily by health care providers.

• 산업경영시스템학회지
• /
• 제23권55호
• /
• pp.33-42
• /
• 2000

It is difficult to estimate the effective factors upon Cumulative Trauma Disorders in real workplace because those are developed by combination of various risk factors for time. The purpose of this paper was to evaluate relative level of CTDs risk factors such as task-related factors, anthropometric factors, joint deviation factors and personal factors using fuzzy linear regression models. And the models are built corresponding to each category with the survey data from telephone operators. The coefficient of fuzzy models are described as the relative level of variable to present risk factors upon CTDs.