• Journal of the Korean Statistical Society
• /
• 제36권3호
• /
• pp.435-445
• /
• 2007

This paper addresses for the first time the use of complete data information criteria in unsupervised learning of the Naive-Bayes model. A Monte Carlo study sets a large experimental design to assess these criteria, unusual in the Bayesian network literature. The simulation results show that complete data information criteria underperforms the Bayesian information criterion (BIC) for these Bayesian networks.

• Journal of the Korean Data and Information Science Society
• /
• 제15권4호
• /
• pp.993-1002
• /
• 2004

Imputation procedures such as fully efficient fractional imputation(FEFI) or multiple imputation(MI) can be used to construct complete contingency tables from samples with partially classified responses. Variances of FEFI estimators of population proportions are derived. Simulation results, when data are missing completely at random, reveal that FEFI provides more efficient estimates of population than either multiple imputation(MI) based on data augmentation or complete case analysis, but neither FEFI nor MI provides an improvement over complete-case(CC) analysis with respect to accuracy of estimation of some parameters for association between two variables like $\theta_{i+}\theta_{+i}-\theta_{ij}$ and log odds-ratio.

• Journal of applied mathematics & informatics
• /
• 제37권3_4호
• /
• pp.207-217
• /
• 2019

We are presented of several basic properties for negatively superadditive dependent(NSD) random variables. By using this concept we are obtained complete convergence for maximum partial sums of rowwise NSD random variables. These results obtained in this paper generalize a corresponding ones for independent random variables and negatively associated random variables.

• Annals of Geriatric Medicine and Research
• /
• 제20권3호
• /
• pp.149-159
• /
• 2016

Background: Since the mid-20th century, the ways in which social networks and older adults' health are related have been widely studied. However, few studies investigate the relationship between self-rated health and position in a complete social network of one entire Korean rural village. This study highlights use of a complete network in health studies. Methods: Using the Korean Social Life and Health Project, the population-based data of adults aged 60 or older and their spouses in one myeon in Ganghwa island (Ganghwa-gun, Incheon, Korea), Incheon, Korea (with a 95% response rate), this study built a $1,012{\times}1,012$ complete social network matrix of the village. The data were collected from 2011 to 2012, and 731 older adults were analyzed. The ordered logistic models to predict self-rated health allowed us to examine social factors from socio-demographic to individual community activities, ego-centered network characteristics, and positions in a complete network. Results: From the network data, 5 network components were identified. Even after controlling for all other factors, if a respondent belonged to a segregated component, the probability that he or she reported good health dropped substantially. Additionally, high in-degree centrality was connected to greater self-rated health. Conclusion: This finding highlights the importance of social position not only from the respondents' point of view but also from the entire village's perspective. Even if a respondent maintained a large social network, when all of those social ties belonged to a segregated group in the village, the respondent's health suffered from this segregation.

• 한국응급구조학회지
• /
• 제9권2호
• /
• pp.79-88
• /
• 2005

The purpose of this study was to develope the Complete Airway Obstruction Maneuver Training Program and identify its effects on learning motivation, knowledge and skill of choking management in the primary school students. The subjects for the experimental group of 38 students and the control group of 39 students, all of whom are primary school students in Gwangju, the Republic of Korea. A non-equivalent control group pretest-posttest design was used and data were collected from November to December, 2003. During about 2 weeks, 2 times for a week with 80 minutes at a time, the complete airway obstruction maneuver training program was conducted in the experimental group. Experimental data were analyzed through SPSS/win 11.0 PC+, and the tests examining general characteristics between the experimental group and the control group were conducted through $x^2$-test. Fisher's exact probability test and t-test, and identifying the effect of the complete airway obstruction Maneuver training program was analysed through t-test and ANCOVA. The results of the study were as follows: 1. After intervention on the complete airway obstruction maneuver training program, Learning motivation in the experimental group was significantly higher than that of the control group. 2. After intervention on the complete airway obstruction maneuver training program, knowledge of choking management the experimental group was significantly higher than that of the control group(F=223.637, p=.000). 3. After intervention on the complete airway obstruction maneuver training program, skill of choking management the experimental group was significantly higher than that of the control group(t=46.800, p=.014). These findings suggest that the complete airway obstruction maneuver training program can facilitate learning motivation, knowledge and skill of choking management in the primary school students. Therefore it is considered that the complete airway obstruction maneuver training program can be utilized as a effective way to implement the 7th national curriculum for creative extra-activities.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 1998년도 춘계 학술발표회 논문집 Proceedings of EESK Conference-Spring 1998
• /
• pp.23-30
• /
• 1998

An estimation of seismic risk parameters by seismic zones of the Korea Peninsula in order to calculate the seismic hazard values using these was erformed. Seven seismic source zones were selected in consideration of seismicity and geology of Korean Peninsula. The seismicity parameters that should be estimated are maximum intensity, activity rate and b value in the Gutenberg - Richter relation. For computation of these parameters, least square method or maximum likelihood method is applied to the earthquake data in two ways; the one for the data without maximum intensity and the other with maximum intensity. Earthquake data since Choseon Dynasty is regarded as complete and estimation of parameters was made for these data using above two ways. And recently, a new method is published that estimate the seismicity parameters using mixed data containing large historical events and recent complete observations. Therefore, this method is applied to the whole earthquake data of the Korean Peninsula. It turns out that the b value computed considering maximum intensity is slightly lower than that computed considering without maximum intensity, and it becomes still lower when the incomplete data prior to Choseon Dynasty is used. In the case of the activity rates, the values obtained without maximum intensity and that with maximum intensity are similar, though they are lower when the incomplete data is used. The values of maximum intensities are usually lower when considering incomplete data. In the seismic source zone including the Yangsan Fault zone, however, the values are higher when considering the incomplete data.

• 보건행정학회지
• /
• 제24권3호
• /
• pp.261-270
• /
• 2014

Background: This study examined what factors affected a complete examination of infant health checkup. Methods: We used Korean national health insurance claim data of 2,936,650 infants, taking examination in 2012. These claim data included enrollment status of householders and records of infant health checkup from 2008 to 2013. Results: Our results shows that for infant characteristics, the likelihood of complete examination of infant health checkup is significantly lower in female, older aged, and handicapped ones. For householder characteristics, the likelihood of complete examination of infant health checkup is also significantly lower in female, older group and self-employed ones. For household characteristics, the likelihood of complete examination is also significantly lower in single-parent families, multi-cultural families, parent with unexperienced health checkup and lower monthly premiums. Conclusion: It is necessary to support an additional use-guide and follow-up management services to improve incomplete examination of infant health checkup.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 춘계학술대회
• /
• pp.213-216
• /
• 2013

인터넷의 발달과 유무선 네트워크 인프라 기술의 발전으로 빅테이터 및 개인정보보의 활용이 많아지고 있다. 하지만 개인정보보호법의 시행에도 불구하고, 개인정보 유출로 인한 침해사고가 발생하고 있다. 개인정보 유출은 개인의 사생활피해와 금융피해로 연관된다. 따라서 개인정보의 탐색 및 검출과정에서 개인정보의 패턴을 분석하여 추출하는 연구와 불필요한 개인정보의 완전삭제에 관한 연구가 필요하다. 본 연구에서는 개인정보보호에 대한 패턴추출 연구와 완전삭제 방법을 연구하여 개인정보의 패턴추출 및 완전삭제 실험을 하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제16권1호
• /
• pp.95-106
• /
• 2005

Complete-case analysis is easy to carry out and it may be fine with small amount of missing data. However, this method is not recommended in general because the estimates are usually biased and not efficient. There are numerous alternatives to complete-case analysis. A natural alternative procedure is available-case analysis. Available-case analysis uses all cases that contain the variables required for a specific task. The EM algorithm is a general approach for computing maximum likelihood estimates of parameters from incomplete data. These methods and multiple imputation(MI) are reviewed and the performances are compared by simulation studies in monotone missing pattern.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.919-925
• /
• 2006

Maximum likelihood estimate(MLE) is obtained from the partial log-likelihood function for the cell probabilities of two way incomplete contingency tables proposed by Chen and Fienberg(1974). The partial log-likelihood function is modified by adding lagrangian multiplier that constraints can be incorporated with. Variances of MLE estimators of population proportions are derived from the matrix of second derivatives of the loglikelihood with respect to cell probabilities. Simulation results, when data are missing at random, reveal that Complete-case(CC) analysis produces biased estimates of joint probabilities under MAR and less efficient than either MLE or MI. MLE and MI provides consistent results under either the MAR situation. MLE provides more efficient estimates of population proportions than either multiple imputation(MI) based on data augmentation or complete case analysis. The standard errors of MLE from the proposed method using lagrangian multiplier are valid and have less variation than the standard errors from MI and CC.