• Journal of the Korean Statistical Society
• /
• 제29권2호
• /
• pp.201-217
• /
• 2000

The method of generalized estimating equations (GEE) has become very popular for the analysis of longitudinal data. We extend this work to the use of M-estimators; the resultant regression estimates are robust to heavy tailed errors and to outliers. The proposed method does not require correct specification of the dependence structure between observation, and allows for heterogeneity of the error. However, an estimate of the dependence structure may be incorporated, and if it is correct this guarantees a higher efficiency for the regression estimators. A goodness-of-fit test for checking the adequacy of the assumed M-estimation regression model is also provided. Simulation studies are conducted to show the finite-sample performance of the new methods. The proposed methods are applied to a real-life data set.

• 한국융합학회논문지
• /
• 제11권5호
• /
• pp.97-105
• /
• 2020

본 연구는 어머니가 지각한 유아의 스마트폰 과의존에 대한 주요 예측요인을 밝혀내고 교육 및 실천현장에 유용한 기초자료를 제공하는 것을 목적으로 수행되었다. 조사대상은 경상북도에 거주하는 만4세-7세 유아의 주양육자인 어머니로 총 410부가 분석에 활용되었다. 데이터마이닝 의사결정나무 분석을 위해 SPSS 23.0 프로그램을 활용하였고, 그 결과는 다음과 같다. 첫째, 전체 유아를 대상으로 보았을 때, 스마트폰 과의존을 가장 중요하게 예측하는 변인은 아버지의 여가활동 양육참여로 나타났다. 둘째, 성별에 따른 차이를 분석한 결과, 남아는 아버지의 여가활동참여가 스마트폰 과의존에 가장 관계가 높은 것으로 나타났다. 하지만, 아버지의 여가활동 참여가 높더라도, 어머니의 과보호와 허용적 태도가 높은 경우 스마트폰 과의존은 다시 증가하였다. 여아의 경우, 스마트폰 과의존에 가장 높은 영향을 미치는 변인은 어머니의 양육태도 중 온정과 격려로 나타났다.

• Tuberculosis and Respiratory Diseases
• /
• 제85권4호
• /
• pp.349-357
• /
• 2022

Background: The most consistently identified mortality determinants for the new coronavirus 2019 (COVID-19) infection are aging, male sex, cardiovascular/respiratory diseases, and cancer. They were determined from heterogeneous cohorts that included patients with different disease severity and previous conditions. The main goal of this study was to determine if activities of daily living (ADL) dependence measured by Barthel's index could be a predictor for COVID-19 mortality. Methods: A prospective cohort study was performed with a consecutive sample of 340 COVID-19 patients representing patients from all over the northern region of Portugal from October 2020 to March 2021. Mortality risk factors were determined after controlling for demographics, ADL dependence, admission time, comorbidities, clinical manifestations, and delay-time for diagnosis. Central tendency measures were used to analyze continuous variables and absolute numbers (proportions) for categorical variables. For univariable analysis, we used t test, chi-square test, or Fisher exact test as appropriate (α=0.05). Multivariable analysis was performed using logistic regression. IBM SPSS version 27 statistical software was used for data analysis. Results: The cohort included 340 patients (55.3% females) with a mean age of 80.6±11.0 years. The mortality rate was 19.7%. Univariate analysis revealed that aging, ADL dependence, pneumonia, and dementia were associated with mortality and that dyslipidemia and obesity were associated with survival. In multivariable analysis, dyslipidemia (odds ratio [OR], 0.35; 95% confidence interval [CI], 0.17-0.71) was independently associated with survival. Age ≥86 years (pooled OR, 2.239; 95% CI, 1.100-4.559), pneumonia (pooled OR, 3.00; 95% CI, 1.362-6.606), and ADL dependence (pooled OR, 6.296; 95% CI, 1.795-22.088) were significantly related to mortality (receiver operating characteristic area under the curve, 82.1%; p<0.001). Conclusion: ADL dependence, aging, and pneumonia are three main predictors for COVID-19 mortality in an elderly population.

• 한국융합학회논문지
• /
• 제12권12호
• /
• pp.583-594
• /
• 2021

본 연구는 병원간호사의 COVID-19 위험인식, 미디어 의존, 정부신뢰, 회복탄력성과 사회심리적 스트레스가 COVID-19 예방행위에 미치는 영향을 파악하고자 수행된 서술적 조사연구이다. 대학병원 간호사 200명을 대상으로 자료수집을 하였고, 수집된 자료는 SPSS 24.0 프로그램을 활용하여 기술통계, t-test, Pearson's 상관관계 분석, ANOVA, 다중회귀분석으로 분석하였다. 대상자의 평균연령은 29.8세, 병원 경력은 6.6년이었고, COVID-19 예방행위는 4.3점으로 높은 편이었다. COVID-19 예방행위는 COVID-19 위험인식, 회복탄력성 및 미디어 의존과는 정적상관관계 사회심리적 스트레스와 부적상관관계를 보였다. COVID-19 예방행위에 영향을 미치는 요인은 COVID-19 위험인식, 회복탄력성, 사회심리적 스트레스, 미디어 의존이었다. 병원간호사의 COVID-19 예방행위가 지속할 수 있도록 COVID-19 위험인식 및 미디어 의존을 적절히 관리하고, 회복탄력성 강화와 사회심리적 스트레스 경감을 위한 중재프로그램의 개발 및 적용이 필요하다.

• 한국컴퓨터정보학회논문지
• /
• 제27권4호
• /
• pp.213-221
• /
• 2022

본 연구의 목적은 아동의 스마트폰 의존도에 따른 학교생활 적응과 학업수행능력 차이를 분석함으로써 스마트기기 과의존 문제를 예방하고 개선할 수 있는 방안을 모색하는 데 있다. 이를 위해 한국아동패널조사 중 12차 년도 초등학교 5학년 학생의 자료를 추출하여 활용하였다. 수집된 자료는 비계층적 군집화분석(K-means), 일원변랑분석(One-way ANOVA)과 사후검증(Scheffé test)를 실시하여 분석하였다. 연구결과는 다음과 같다. 첫째, 스마트기기 의존과 학교적응 및 학업수행능력은 부적 상관관계가 있는 것으로 나타났다. 둘째, 스마트기기의 의존도가 높은 잠재적 위험군과 고위험군의 학생이 안전군의 학생과 비교해 학교적응이 유의하게 낮은 것으로 나타났다. 셋째, 고위험군의 학생이 잠재적 위험군과 일반군의 학생과 비교해 학업수행능력이 유의하게 낮게 나타났다. 이와 같은 연구결과를 바탕으로 스마트기기 과의존 초등학생을 위해서는 다양한 학습지원과 더불어 학교생활 적응 상담 지원 같은 국가 차원의 노력이 필요함을 제언하였다.

• Communications for Statistical Applications and Methods
• /
• 제28권1호
• /
• pp.59-79
• /
• 2021

Value at Risk (VaR) is one of the most common risk management tools in finance. Since a portfolio of several assets, rather than one asset portfolio, is advantageous in the risk diversification for investment, VaR for a portfolio of two or more assets is often used. In such cases, multivariate distributions of asset returns are considered to calculate VaR of the corresponding portfolio. Copulas are one way of generating a multivariate distribution by identifying the dependence structure of asset returns while allowing many different marginal distributions. However, they are used mainly for bivariate distributions and are not widely used in modeling joint distributions for many variables in finance. In this study, we would like to examine the performance of various copulas for high dimensional data and several different dependence structures. This paper compares copulas such as elliptical, vine, and hierarchical copulas in computing the VaR of portfolios to find appropriate copula functions in various dependence structures among asset return distributions. In the simulation studies under various dependence structures and real data analysis, the hierarchical Clayton copula shows the best performance in the VaR calculation using four assets. For marginal distributions of single asset returns, normal inverse Gaussian distribution was used to model asset return distributions, which are generally high-peaked and heavy-tailed.

• 산경연구논집
• /
• 제9권3호
• /
• pp.45-56
• /
• 2018

Purpose - The Korean university education system is facing innovation and change, including cooperation between industry and university, Therefore It is important to activate the industry-university cooperation. This paper aims to demonstrate the factors that activate industry-university cooperation, particularly about the voluntary participation induction by industry and researching in path dependency perspectives. Research design, data, and methodology - The subject of this research were companies that are aware of the industry-university cooperation program. This research hypothesis is derived from the literature of previous studies of industry-university cooperation, This study have constructs that was defined operationally with reference to previous studies, this research model design to figure out structural relationship among technology leadership of university, university specialization, local network strength, fixation of local economy, recognition of path dependence, participation by industry, performance of industry-university cooperation. From 2017 July. 1 to Sept. 31, questionnaire survey targeting company staff who is involving in industry-university cooperation. 257 questionnaire survey had conducted. 249 investigated data were used for empirical analysis except wrong data. This data were used for AMOS(structural equation) & Regression statistics to verify hypothesis which developed by researcher. Results - The results of this study are as follows. First, technology leadership of universities has a significant effect on voluntary participation by industry. University specialization has significant effect on voluntary participation by industry. Second, local network strength has significant effect on voluntary participation by industry. but fixation of local economy does not affect voluntary participation by industry. Third, recognition of path dependence has moderating effect between Independent(university, company characteristics) and dependent variables(voluntary participation by industry) When recognition level of path dependence is high, preceding factors have a significant effect on voluntary participation by industry than recognition level of path dependence is low. As a result, the degree of recognition of path dependence was shown important variables that induce voluntary participation of industry for industry-university cooperation program. Conclusions - This study suggests that voluntary participation of industry is a very important factor in the achievement of industry-university cooperation. Recognition of interdependence as well as leading factors that encourage voluntary participation of industry is also just as important. If recognition of path dependence was high, Industry's voluntary participation was high.

• 한국가스학회지
• /
• 제1권1호
• /
• pp.7-13
• /
• 1997

최소발화에너지의 압력의존성을 고찰하기 위해 열발화이론, 열전달개념, 이상기체법칙, 그리고 반응속도론에 의해 시도하였다. 최소발화에너지와 압력의 상관관계식을 문헌자료의 다중회귀분석을 통하여 수식화하였다. 이 방법에 적용한 물질은 대표적인 탄화수소인 프로판과 노말펜탄이었다. 제시된 방법론에서 압력변화에 따른 예측된 최소발화에너지는 아주 작은 평균오차에서 문헌값과 일치하고 있다. 따라서 제시된 방법론은 탄화수소의 최소발화 에너지를 예측하는 일반적인 방법으로 제시하고 있다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권4호
• /
• pp.1285-1288
• /
• 2012

Background: The Fagerstrom Test for Cigarette Dependence (FTCD) (formally FTND) is widely used for measuring physical dependence on nicotine. Objective: To explore the cross cultural validity and reliability of FTCD amongst Arabic speaker cigarette consumers who chew khat leaf, a stimulant green leaf. Methods: The psychometric properties of the FTCD were assessed in a subsample (91regular cigarette smokers) of purposively selected 204 UK-resident Yemeni khat chewers recruited during random visits to khat sale outlets. Data were collected via a structured face-to-face interview. Data analyses included descriptive tests and factor analysis. Results: Two factors were obtained by a principle axis factor analysis and these were termed as urgency of restoring the level of nicotine after abstinence during sleeping and maintaining the level of nicotine during waking. The internal reliability (Cronbach's alpha coefficient) of the whole FTCD is low (.68) as well as for the two subscales (.60) and (.62) respectively. Conclusion: The psychometric properties of the Arabic version of the FTCD scale in this sample of Yemeni khat chewers who smoked regularly confirmed what has been established in other cultural settings. The findings of this study have yet to be cross validated amongst other appropriately representative sample of Arabic speakers.

• 통상정보연구
• /
• 제16권2호
• /
• pp.199-218
• /
• 2014

본 연구는 1995년부터 2010년까지 국가 에너지통계의 에너지소비, 생산, 수출 입 등 실적자료를 바탕으로 우리나라의 에너지경제효율을 분석하였다. 에너지 수출 입과 에너지 생산 자료를 통해 에너지원단위, 에너지순수입의존도, 에너지자립도 I, II 를 산출하고 국가경제규모와 비교분석을 통해 우리날 에너지경제 수준을 살펴보고 시사점을 제시하는데 목적이 있다. 에너지원단위 지표를 통한 에너지효율수준 분석이 주로 이루어졌다면, 본 연구는 에너지순수입의존도와 에너지자립도를 통해 국가 에너지 수출 입구조와 에너지생산수준을 추가적으로 살펴볼 수 있는 장점이 있다고 하겠다. 연구 결론으로 우리나라는 에너지경제효율 수준이 상당히 낮은 수준으로 국가적 정책 차원의 에너지효율개선의 필요성을 제기한다.