• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1161-1165
• /
• 2006

본 연구는 OLS 및 변수선택법에 의해 통계학적 모형의 매개변수를 산정하여 모형의 적용성을 입증하고 하천 주요지점에 대한 홍수위 예측을 통해 홍수예보 및 예측 업무에 기여코자하는데 연구목적이 있다. 다중선형회귀모형을 구성하기 위한 독립변수는 예보지점의 수위/유출량 자료와 상류지점의 수위/유출량 자료, 그리고 유역의 선행 평균강우량 등의 자료를 독립변수로 하여 통계학적 홍수예측을 위한 다중선형 회귀모형을 각각 구성하여 적합성 여부를 판단하였다. 매개변수 산정은 OLS(Ordinary least square root method)와 변수선택(Stepwise)방법에 의해 산정하였으며, 중랑천 유역의 2002년부터 2005년까지의 수문사상 16개를 선정하여 모형에 적용한 결과 두 매개변수 산정방법 모두 30분에서 90분 예측은 상대적으로 정확한 결과를 나타내었으며, OLS 및 변수선택법에 의한 매개변수 산정결과 변수선택법에 의한 방법이 OLS 방법보다는 상관성이나 효율지수면에서 조금 더 정확한 값을 나타내고 있으나 독립변수의 일관성을 감안한다면 변수선택법보다는 OLS방법에 의한 매개변수 산정이 타당할 것으로 사료된다. 기존의 홍수예보 업무에 활용되고 있는 수문학적 홍수예측 모형인 저류함수법의 여러 매개변수 조정에 의한 홍수위 예측 방법보다는 비교적 간단한 통계적 방법에 의한 홍수위 예측 방법으로 홍수예보의 선행시간 확보가 필수적인 중랑천과 같이 유역면적이 작은 중소하천에서의 홍수예보 업무에 효과적으로 이용 가능할 것으로 사료된다.

• The Korean Journal of Rehabilitation Nursing
• /
• v.7 no.2
• /
• pp.188-196
• /
• 2004

Purpose: This study was conducted to identify relationships between depression, family support, and rehabilitation-motivation in patients with cerebrovascular accident. Method: The data were collected from 'S' hospital in Seoul from Feb. 1, 2004 to Apr. 30, 2004. The data were analyzed using a SPSS 10.0 program for descriptive statistics, Pearson correlation coefficients and stepwise multiple regression. Result: The results were as follows: The mean rehabilitation-motivation was 119.89, which was slightly high. The rehabilitation-motivation was influenced by religion, education level, occupation, economic status, treatment fee, duration of hospitalization, level of language ability and ADL. Rehabilitation-motivation has showed correlation with family support (r=.538, p=.000) and depression (r=-.417, p=.000). The variables related to rehabilitation-motivation were identified as family support, level of ADL, occupation, depression, and education level, using stepwise multiple regression. They were accounted for 57% of predictability of the rehabilitation-motivation, with the family support the highest at 29.3%. Conclusion: With increasing post stroke patients in Korea, we need to pay more attention to the rehabilitation of them. This study indicates that health professionals need to focus on the intervention especially in increasing family support and in decreasing depression of the patients with cerebrovascular accident.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.6
• /
• pp.1939-1944
• /
• 2011

The nucleophilic substitution reactions of bis(Y-aryl) chlorophosphates (1) with substituted anilines and deuterated anilines are investigated kinetically in acetonitrile at 35.0 $^{\circ}C$. The kinetic results of 1 are compared with those of Y-aryl phenyl chlorophosphates (2). The substrate 1 has one more identical substituent Y compared to substrate 2. The cross-interaction between Y and Y, due to additional substituent Y, is significant enough to result in the change of the sign of cross-interaction constant (CIC) from negative ${\rho}_{XY}$ = -1.31 (2) to positive ${\rho}_{XY}$ = +1.91 (1), indicating the change of reaction mechanism from a concerted $S_N2$ (2) to a stepwise mechanism with a rate-limiting leaving group departure from the intermediate (1). The deuterium kinetic isotope effects (DKIEs) involving deuterated anilines ($XC_6H_4ND_2$) show secondary inverse, $k_H/k_D$ = 0.61-0.87. The DKIEs invariably increase as substituent X changes from electron-donating to electron-withdrawing, while invariably decrease as substituent Y changes from electron-donating to electron-withdrawing. A stepwise mechanism with a rate-limiting bond breaking involving a predominant backside attack is proposed on the basis of positive sign of ${\rho}_{XY}$ and secondary inverse DKIEs.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.16 no.2
• /
• pp.67-75
• /
• 2010

Purpose: The purpose of this is to identify the relationship among the age, body mass index(BMI) and exercise frequency(EF) with knee joint position sense in korean healthy women. Methods: Healthy women of 328 who participated in this study were tested knee joint position sense; reposition error was measured with a Myrin goniometer. Each reposition error was analyzed using descriptive statics, pearson correlation coefficients, and stepwise multiple regression. Results: The mean reposition error by age groups was significant decrease getting older. The mean reposition error by BMI groups was significant decrease getting higher. And the mean reposition error by EF groups was significant decrease getting lower. The knee joint position sense showed a significantly correlation with age(r=0.36, p=.00), BMI(r=0.34, p=.00) and EF(r=-0.50, p=.00). The most powerful predictor of knee joint position sense was EF. The reposition error according to stepwise multiple regression is $3.36+(-2.64){\times}EF+0.13{\times}age$, and account for 46%($R^2=0.46$) of the variance in the knee joint position sense. Conclusion: The older the women are, for prevent of knee injuries due to decreased joint position sense, regular exercise is essential factor.

• Research in Community and Public Health Nursing
• /
• v.22 no.1
• /
• pp.75-85
• /
• 2011

Purpose: The purpose of this study was to describe the status of the functional health literacy of the elderly living in a rural community and to identify the influencing factors on the functional health literacy. Methods: Subjects(n=238) aged over 60 years were selected for data collection. Functional health literacy was measured by Korean Health Literacy, which consisted of 15 items including eight numeracy and seven comprehension items. Descriptive statistics, t-test, ANOVA with Scheffe test, and stepwise multiple regression were used to analyze the data. Results: The mean score of total functional health literacy was $6.66{\pm}3.31$, numeracy was $3.52{\pm}1.76$, and comprehension was $3.41{\pm}2.10$. Of the subjects, 39.1% showed a low score below the median split. In the results of stepwise multiple regression, the factors affecting functional health literacy were basic literacy, age, number of chronic diseases, self-reported health status, and gender. These factors accounted for 33.0% of functional health literacy. Conclusion: These results suggest that interventions for improving functional health literacy are necessary to enhance elders' ability of self-care management. In addition, it is needed to take into account the individual characteristics of the subjects depending on their gender, age, and health status.

• Journal of Korean Public Health Nursing
• /
• v.28 no.3
• /
• pp.509-521
• /
• 2014

Purpose: This study was conducted in order to define factors influencing learned helplessness in undergraduates. Independent variables including external entrapment, internal entrapment, social support, trait anger, state anger, and anger expression were used to predict learned helplessness. Methods: Data were analyzed using the SPSS/WIN 20.0 program for descriptive statistics, Pearson correlation coefficients and stepwise multiple regression. A total of 241 undergraduates recruited from September to November 2012 were included in the study. Results: Four factors of learned helplessness were founded to show significant correlation with external entrapment, internal entrapment, social support, trait anger, state anger and anger expression. Stepwise multiple regression analysis showed that 64% of the variance in learned helplessness was significantly accounted for by internal entrapment, social support and anger expression. Conclusion: This study showed that perceived entrapment and social support are important predictors of learned helplessness. Therefore, in order to reduce learned helplessness in undergraduates, it is necessary to design an intervention program with strategies to help in coping with and reducing perceived entrapments.

• Korean Journal of Human Ecology
• /
• v.23 no.2
• /
• pp.251-268
• /
• 2014

Applying the data from 64 single(26 men and 38 women) and 71 childless married men and women(37 men and 34 women) aged between 30 and 45, this study is to understand their future fertility intention. For this purpose, ideal and real number of children that participants plan to have were compared using paired t-test. Second, demographic variables(sex, age, marital status), child care related variables(thoughts about caring children, child care value), individual characteristics(gender role attitude, relation orientation) and social context variables(perceived economic condition, recognition of low fertility policies) were included in a stepwise regression model to explain expected number of children participants plan to have in the future. Results showed that ideal number of children participants wish to have was significantly higher than real number of children they expect to have in the Korean society. The stepwise regression model explained 35% of the variance of the dependent variable. Among four types of variables, child care related variables most powerfully explained expected number of children study participants plan to have in the future. Finally, age, child care value, gender role attitude, and relation orientation significantly explained expected number of children in the future.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.6
• /
• pp.361-368
• /
• 2002

This paper presents a new data path synthesis algorithm which takes into account simultaneously three important design criteria: testability, design area, and total execution time. We define a goodness measure on the testability of a circuit based on three rules of thumb introduced in prior work on synthesis for testability. We then develop a stepwise refinement synthesis algorithm which carries out the scheduling and allocation tacks in an integrated fashion. Experimental results for benchmark and other circuit examples show that we are able to enhance the testability of circuits with very little overheads on design area and execution time.

• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.195-198
• /
• 2004

One Important problem in a cancer microarray study is to identify a set of genes from which a molecular prognostic indicator can be developed. In parallel with this problem is to validate the chosen set of genes. We develop in this note a K-fold cross validation procedure by combining a 'pre-validation' technique and a bootstrap resampling procedure in the Cox regression . The pre-validation technique predicts the microarray predictor of a case without having seen the true class level of the case. It was suggested by Tibshirani and Efron (2002) to avoid the possible over-fitting in the regression in which a microarray based predictor is employed. The bootstrap resampling procedure for the Cox regression was proposed by Sauerbrei and Schumacher (1992) as a means of overcoming the instability of a stepwise selection procedure. We apply this K-fold cross validation to the microarray data of 92 gastric cancers of which the experiment was conducted at Cancer Metastasis Research Center, Yonsei University. We also share some of our experience on the 'false positive' result due to the information leak.

• Journal of Korean Clinical Health Science
• /
• v.2 no.3
• /
• pp.176-187
• /
• 2014

Purpose. The purpose of this study was to identify the factors affecting quality of sleep and sleep disturbance among inpatient. Methods. A descriptive correlational study was conducted Participants were 200 inpatient in a hospital located in B city. A structured questionnaire was used for data collection. Collected data were analyzed using descriptive statistics, t-test, one-way ANOVA, Pearson's correlation, and stepwise multiple regression. Result. Hospitalized patient's score of sleeping quality was 38.26 on an overall scale of 60, indicating it to be higher than 'Medium (30 points). Almost hospitalized patient in this study suffer from sleep disturbances. As results of univariate analyses, Educational level, Departments, Why hospitalized, Insomnia / depression, Chronic Disease, Scale of pain, physical symptoms, environmental factors, emotional factors, and sleep promoting behavior, disturbed sleep among hospitalized. However, the result of stepwise multiple regression analysis identified that physical symptoms, environmental factors, emotional factors, sleep promoting behavior, and Why hospitalized disturbed sleep and were significant score of sleeping quality for hospitalized and these sleep disturbance factors accounted 46.8% of variance of sleeping quality among hospitalized. Conclusion. These findings suggest that hospitalized patients with poor sleep quality should have their health carefully screened for physical symptoms, environmental factors, emotional factors, sleep promoting behavior, and why hospitalized. In addition, we recommend the development of a nursing program for improving sleep quality.