• Communications for Statistical Applications and Methods
• /
• 제25권6호
• /
• pp.605-618
• /
• 2018

Risk management has been a crucial part of the daily operations of the financial industry over the past two decades. Value at Risk (VaR), a quantitative measure introduced by JP Morgan in 1995, is the most popular and simplest quantitative measure of risk. VaR has been widely applied to the risk evaluation over all types of financial activities, including portfolio management and asset allocation. This paper uses the implementations of multivariate GARCH models and copula methods to illustrate the performance of a one-day-ahead VaR prediction modeling process for high-dimensional portfolios. Many factors, such as the interaction among included assets, are included in the modeling process. Additionally, empirical data analyses and backtesting results are demonstrated through a rolling analysis, which help capture the instability of parameter estimates. We find that our way of modeling is relatively robust and flexible.

• Journal of Information Science Theory and Practice
• /
• 제10권4호
• /
• pp.38-52
• /
• 2022

Since older people are traditionally considered disadvantaged when it comes to Internet use, it is useful to examine whether older individuals use the Internet for health information seeking (HIS). This study aims to investigate digital inequalities in terms of Internet use by older population for HIS in the European region. As methods, we applied secondary data analysis (of Eurostat data) to investigate the influence of age, educational level, sex, and countries' wealth. Cluster analysis combined with multidimensional scaling was used to find out those countries exhibiting similarities in older people's online HIS. The main results are: Older individuals do not equally use the Internet in general and for HIS in particular. Older Internet users with higher level of education and of the female sex are more likely to use the Internet for health information.

• International Journal of Contents
• /
• 제16권4호
• /
• pp.39-49
• /
• 2020

The goal of this research was to understand the patterns of multidimensional engagement in MOOCs. An email with an online survey link was sent to enrollees in an MOOC course. The survey included 35 questions asking about engagement, teaching presence, and learning persistence. The items were validated in the literature, revised for the MOOC setting, reviewed by four professionals in the field of educational technology, and used in the study. A heterogeneous group of 170 individuals gathered through convenience sampling participated in the study. With cluster analysis of the engagement data, three groups were identified: Cluster1, 2, and 3. Cluster 1 scored high on behavioral, emotional, and cognitive engagement. Cluster 2 scored high on behavioral aspects but low on emotional and cognitive engagement. Cluster 3 scored low on behavioral and cognitive engagement but high on emotional aspects. The study addressed cluster-specific learner characteristics and differences in perceived teaching presence and learning persistence. Design strategies pertaining to each cluster were further discussed. These strategies may guide instructors and practitioners in the design and management of MOOCs and should be further validated through future studies.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제61차 동계학술대회논문집 28권1호
• /
• pp.133-134
• /
• 2020

본 논문에서는 낙후된 운전면허 학원 시스템 개선을 위한 운전면허 수험생 맞춤관리 어플리케이션을 제안한다. 제안하는 어플리케이션은 수강생 맞춤 가이드, 후기 서비스, 스케줄 조정, 채점표 제공 등의 다양하고 체계적인 서비스를 도입하여 기존의 시스템을 효과적으로 개선한다. 또한 기존에 개발되어 있는 운전면허 관련 어플리케이션과 달리 오프라인에서만 가능했던 부분까지 온라인 맞춤 관리로 포함하여 개발함으로서 사용자의 만족도를 향상시키도록 한다.

• 한국비블리아학회지
• /
• 제24권4호
• /
• pp.99-113
• /
• 2013

본 연구는 학술지를 이용한 동시인용분석을 통해 문헌정보학 분야의 지적구조를 분석하고자 하였다. Journal Citation Reports의 Journal Impact Factor를 바탕으로 선택한 문헌정보학 분야의 30개 학술지를 대상으로 조사된 동시인용 수치를 이용하여 네트워크 분석을 시행하였으며, 이 연구의 결과를 통해 어떤 학술지가 이 분야의 주요한(core) 학술지이며 그렇지 않은 학술지는 어떤 것들이 있는지 파악할 수 있다. 네트워크 분석을 통해 비교적 간단한 방법으로 얻어진 결과임에도 불구하고, 군집분석이나 다차원축적법 같은 통계적 접근법을 통한 대부분의 지적구조분석과 매우 유사한 결과를 보여주었다.

• 한국도서관정보학회지
• /
• 제32권3호
• /
• pp.169-197
• /
• 2001

학문의 연구동향 및 연구변화가 문헌의 서지적 현상 속에 숨겨져 있을 것이라는 가설아래, 1990년대의 한국문헌정보학의 지적구조 및 변화를 저자동시인용분석을 통하여 규명해 보았다. 3개 학회지(한국 문헌정보학회지, 정보관리학회지, 한국도서관 정보학회지)의 10년분을 통해 선정된 50명의 저자를 대상으로 다차원축척기법에 의한 저자간의 상관관계, 군집분석에 의한 저자군집, 요인분석에 의한 하위주제영역, 교차분석에 의한 전체주제영역 및 하위주제영역의 변화추이 등을 구체적으로 분석하였다.

• 전자공학회논문지
• /
• 제49권9호
• /
• pp.196-204
• /
• 2012

최근 많은 응용 분야에서 대규모 데이터에 대해 온라인 다차원 분석(OLAP)을 사용하고 있다. 다차원 데이터 큐브는 OLAP 분석에서 핵심 도구로 여긴다. 본 논문에서는 맵리듀스 분산 병렬 처리를 이용하여 효율적으로 데이터 큐브를 계산하는 방법을 연구하고자 한다. 이를 위해, 맵리듀스 프레임워크에서 데이터 큐브 계산 방법으로 잘 알려진 PipeSort 알고리즘을 구현하는 효율적인 방법에 대해서 살펴본다. PipeSort는 데이터 큐브의 한 큐보이드에서 동일한 정렬 순서를 갖는 여러 큐보이드를 한 파이프라인으로 한꺼번에 계산하는 효율적인 방식이다. 이 논문에서는 맵리듀스 프레임워크에서 PipeSort의 파이프라인을 구현한 네 가지 방법을 20대의 서버에서 수행하였다. 실험 결과를 보면, 고차원 데이터에 대해서는 PipeMap-NoReduce 알고리즘이 우수한 성능을 보였으며, 저차원 데이터에 대해서는 Post-Pipe 알고리즘이 더 우수함을 보였다.

• 응용통계연구
• /
• 제31권1호
• /
• pp.67-75
• /
• 2018

다차원척도법은 개체간의 비유사성을 저차원 공간에 기하적으로 표현하기 위한 다변량 자료의 탐색적 분석기법이다. 그러나 일반적인 다차원척도그림에서는 개체들의 유사성 정보만이 표현될 뿐 변수와 관련된 정보가 나타나지 않기 때문에 그림의 해석 상에 한계점이 존재한다. 본 연구에서는 범주형 자료를 다중표시행렬로 변환하고 Torgerson (1958)의 알고리즘에 의한 다차원척도법을 적용하여 개체들의 군집화 성향과 군집들의 상대적 크기를 다차원척도그림으로 시각화하였다. 그리고 Shin 등 (2015)의 분할법을 적용하여 범주형변수의 범주수준별 정보를 다차원척도그림 상에 투영하여 추가적인 정보를 표현하였다. 따라서 본 연구에서 제안하고자 하는 다차원척도그림을 이용하면 개체들의 유사성 정보와 함께 범주형변수들 사이의 연관성도 탐색할 수 있는 장점이 있다.

• 성인간호학회지
• /
• 제23권4호
• /
• pp.363-373
• /
• 2011

Purpose: Fatigue is a common problem in Parkinson's disease (PD), affecting 30~65% of patients with that diagnosis. Only recently has fatigue been recognized as an important clinical feature of PD. The aim of this study was to investigate the level of fatigue and related factors in patients with PD. Methods: Between March 1, and September, 30, 2010, a sample of 181 PD patients agreed to be interviewed. Results: The female patients' PFS (Parkinson Fatigue Scale) score was higher than those of the male patients. Household income and having a Job were significantly correlated with the PFS scores. Among the disease characteristics, motor fluctuations, dyskinesia and modified Hoehn and Yahr stage were significantly correlated with the PFS scores. On stepwise regression analysis, the most important factors related to the PFS scores were depression and sleep disturbance. Conclusion: Fatigue in patients with PD was associated with many factors and strongly associated with depression and sleep disturbance. Fatigue is a multidimensional construct; therefore, multidimensional strategies for relieving specific aspects of fatigue are needed.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권1호
• /
• pp.571-578
• /
• 2013

Background: Patients with breast cancer can experience a feeling of hopelessness very deeply in the adjustment process, and the social support provided during this period can be effective in increasing the level of hope. The present study aimed to identify breast cancer patients' social support and hopelessness level. Materials and Methods: The target population of this analytical study was all breast cancer patients (total of 85) who had treatment in the oncology department of a university hospital located in Adana/Turkey and who met the inclusion criteria. Data were collected through "Personal Information Form", "Beck Hopelessness Scale (BHS)" and "Multidimensional Scale of Perceived Social Support" (MSPSS). Analysis was performed using Shapiro Wilk, One Way ANOVA Welch, Student t-test, Mann Whitney U, and Kruskall Wallis tests. Homogeneity of variance was tested with the Levene, Bonferroni and Games Howell tests. Mean scores and standard deviation values are given as descriptive statistics. Results: Average age of the participants with breast cancer is $48.6{\pm}10.6$. Of all the participants, 84.7% are married, 49.4% graduated from primary school, 81.2% are housewives, and 82.4% had children. The participants' multidimensional perceived social support total scores were found to be high ($57.41{\pm}13.97$) and hopelessness scale scores low ($5.49{\pm}3.80$). There was a reverse, linear relationship between hopelessness scale scores and social support total scores (r=-0.259, p=0.017). A statistically significant relationship was found between hopelessness scores and education level and having children, occupation, income status, and education level of spouses (p<0.05). Conclusions: The present study indicates that hopelessness of the patients with breast cancer decreased with the increase in their social support. Therefore, activating patient social support systems is of importance in increasing their level of hope.