• Journal of the Korean Statistical Society
• /
• v.30 no.3
• /
• pp.499-509
• /
• 2001

We investigate the influence of observations on a test of additional information about discrimination using the influence function and the derivative influence measures. the influence function for the test statistic is derived and this sample versions are used for influence analysis. The derivative influence measures for the test statistic under a perturbation scheme are derived. It will be seen that the influence function method and the derivative influence measures yield the same result. Furthermore, we will derive the relationships between the influence function and the derivative influence measures when the sample size is large. an illustrative example is given and we will compare the results provided by the influence function method and the derivative influence measures.

• Journal of Preventive Medicine and Public Health
• /
• v.23 no.4 s.32
• /
• pp.436-450
• /
• 1990

This study was designed to investigate the mar factors affecting selection of delivery facilities by pregnant women. Five hundred women hospitalized at 23 Seoul-area delivery facilities, such as university hospitals, general hospitals, hospitals, and clinics were selected and given questionnaires from April 24 to May 7, 1990. A total of 350 questionnaires were collected and analysed for the study. The results are as follows ; 1. In general, variables which significantly affected the choice of delivery facilities included the age of women, their educational level, the educational level of their husbands, monthly average incomes and residential areas. 2. In analyzing the obstetrical characteristics of the women, those variables significantly affecting the choice of delivery facilities were the gestational period, the facilities for prenatal care, the frequency of prenatal care, the type of delivery, the frequency of miscarriage, previous delivery experiences and the awareness on prenatal care. 3. In comparing the motivation factors for selecting the delivery facilities, all the factors except convenience and need for hospitalization differed significantly among delivery facilities. 4. The factor analysis was assessed for twenty possible factors motivating the choice of delivery facilities. Six factors including personal service, scale of the facility, reputation, urgency, convenience, and experience were noted explaining by 57.7%. 5. In the discriminant analysis used to clarify the major factors affecting the selection of delivery facilities, the 16 significant variables were regarded as independent variables, and the type of delivery facilities was considered a dependent variable. The stepwise method was applied to the analysis. Detected discriminant variables were the facilities for prenatal care, scale factor, personal service factor, urgency factor, convenience factor, reputation factor, experience factor, gestational period, types of delivery, frequency of miscarriage, age and income. These 12 discriminant variables were tested, with reference to discriminant prediction, on their importance in the choice of the delivery facility, by the discriminant functional formula. The test showed a hit-rate of 67.7%. The results suggest that general characteristics, obstetrical characteristics, and motivations for selecting the delivery facilities differ significantly according to the types of the delivery facilities. This study implies that all types of delivery facilities should attempt to acommodate characteristics and motivations of pregnant women. The facilities should be prepared to increase their patients satisfaction with required medical conditions by improving service and responding to the pregnant women's preferences.

• Journal of Korean Academy of Nursing
• /
• v.16 no.2
• /
• pp.44-52
• /
• 1986

Maternal and child health(MCH) status is considered as an important indicator of the level of health and civilization of a community and a country. MCH services for the rural population in the remote ar deserves priority by the government, since more than half(52.9%) of the delivery was occured at home and almost half (45.5%) of the delivery was assited by family members or neighbors. The purpose of the study was to analyse the health fare behavior related to pregnancy and delivery, which can be contributed maternal health care policy mating for the rural people. Specifically, it was intended to analyze the variables which affect the health care behavior in selecting birth places and birth attendants. This study utilized the data which had been already collected for an experimental study on primary health program model in Korean rural communities, funded by the USAID. 184 sample households with women who had delivered a baby during March 1982 to February 1983 were selected. Discriminant Analysis was employed for statistical analysis by utilizing SPSS computer package program. Birth places and birth attendants were considered as dependent variables. Among 12 independent variables in 5 groups considered, 7 independent variables were found statistically significant to affect the selection of birth place. Significant variables by the order of importance are mother's age, order of baby, number of prenatal care, accessibility of emergency medical care, coverage of medical insurance, mother's membership in community organization and husband's educational level. The degree of correct classification of the grouped cases by employing a discriminant . analysis was significantly improved to 78.2％ in comparison to Cmax（56%) and Cpro(51%). Policy implications for each significant variable were discussed to improve the maternal and child health. in Korean ruralarea.

• Journal of Gifted/Talented Education
• /
• v.24 no.4
• /
• pp.679-701
• /
• 2014

As the validity issue of teacher nominations for the identification of gifted students has been raised recently, this study purports to test the validity of teacher nominations for selecting scientifically gifted students. As the criterion variables, domain specific traits such as science creative problem solving skills and science attitudes and domain general characteristics such as divergent thinking skills, creative attitudes, intrinsic motivation, and leadership were analyzed. Scientifically gifted students, potentially gifted students who had never been enrolled in gifted programs but were nominated as the scientifically gifted by teachers, and general class students participated in the study. The results of ANOVA showed that there were significant differences in all variables but originality factors of the TTCT and science creative problem solving skill test between gifted/nominated students and general class students; gifted/nominated students were significantly superior in these variables to general class students. The discriminant functions analysis yielded a discriminant function that significantly discriminated between gifted/nominated and general class students. Variables loaded on the discriminant function were science creative problem solving skills except for the originality subfactor, and science efficacy. These results imply that while teachers are likely to consider adaptation-oriented academic excellency related to logical thinking skills, problem solving skills, and science performance when nominating students, they may ignore the innovation-oriented property which is indicated as the fluency and originality factors of TTCT. Also, the criteria of teacher nominations are presumed to be congruent with the selection criteria of the gifted education program which pursued academic excellency as the educational goal. This suggests that with such criteria, high performing students in the science area can be sufficiently identified by teachers with no further identification procedures or/and tests.

• The Korean Journal of Applied Statistics
• /
• v.11 no.2
• /
• pp.435-449
• /
• 1998

In this article we have introduced a Bayes criterion for the variable selection in multiple discriminant analysis (MDA). The criterion is a default Bayes factor for the comparision of homo/heteroscadasticity of the multivariate normal means. The default Bayes factor is obtained from a development of the imaginary training sample method introduced by Spiegelhalter and Smith (1982). Based an the criterion, we also provided a test for additional discrimination in MDA. The advantage of the criterion is that it is not only applicable for the optimal subset selection method but for the stepwise method. More over, the criterion can be reduced to that for two-group discriminant analysis. Thus the criterion can be regarded as an unified alternative to variable selection criteria suggested by various sampling theory approaches. To illustrate the performance of the criterion, a numerical study has bean done via Monte Carlo experiment.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Journal of Korean Public Health Nursing
• /
• v.2 no.2
• /
• pp.5-20
• /
• 1988

This study is a series of reviews in connection with the application of the Questionnaire THI, in order to intend to provide such datum to be of a help as the screening-test by means of getting through comparative analysis, and finding out existence of any disease appeared as a result of the general medical examinations, and the psychosomatic symptoms, through the questionnaire THI. This study had been researched through the 507 insureds of the life insurance residing in Seoul and in the suburbs of Seoul, during the period 5 Jan. 1987 to 27 Feb. through the questionnaires. Exception of the 88 insincere respondents out of the total objectives, the 419 questionnaires were nanlized through percentage, Mean, T-test, ANOVA test, and Discriminant Analysis. 1. The Subjective Health Problem of the Objectives: The average of the health problem appliation quorum appeared to be 1. 81, the articles of both nervousness and aggressiveness appeared to be each 2.25 and 2.04. It tells that the state of appliation is heavy. It was very significant statistically the relation between the elements of sex, ages, educational backgrounds and occupations. 2. The result of the General Examination of the Objectives: The number of the persons with abnormal findings was 300 persons among the total of 419 persons as a result of the general medical examinations, and it was applicable to $73.5\%$. By each age and marital state were statistically significant. 3. Comparison of the result of the General Examination and Subjective Health of those Objectives: As a result of discriminant analysis of the independent variables through the result of the general examination, the greatest element for influence appeared to be the age, and then, regular examination, sex, and the somatic complaints of the THI in order. Accordingly, it is considered to be able to function as the screening test of the general examination, the THI. In case of a greater unit of group required a medical examination, It is considered to be of a help for the health management service for more effective and precise in quality and economic, only if a medical examination is carried out after selecting the somatic subjective problem and research in advance to the application of the THI prior to the examination.

• Journal of Distribution Research
• /
• v.17 no.3
• /
• pp.59-92
• /
• 2012

With accumulated research evidence, there is little doubt that leadership behavior is related to a wide variety of positive individual and organizational outcomes. Indeed, leadership behavior has been empirically linked to increased employee satisfaction, organizational commitment, extra effort, turnover intention, organizational citizenship behavior, and overall employee performance. Although leadership behavior has been linked to a number of positive organizational outcomes, research regarding the antecedents of such behavior is limited. Especially there is little research dealing with the antecedents of inter-organizational leadership behavior. This study interests in inter-organizational ethical leadership among marketing channel members. In both the mass media and the academic association, there has been a surge in interest in the ethical and unethical behavior of leaders. Although the corporate scandals in recent years may explain much of the mass media and popular focus, academics' interest has been limited by evidence that ethical leadership behavior is associated with both positive and negative inter-organizational processes and performances. This study tried to contribute to this body of knowledge by examining antecedents of ethical leadership. Ethical leadership is defined "the demonstration of normatively appropriate conduct through personal actions and interpersonal relationships, and the promotion of such conduct to followers through two-way communication, reinforcement, and decision-making." Ethical leaders not only inform individuals of the behefits of ethical behavior and the cost of inappropriate behavior, such leaders also set clear standards and use rewards and fair and balanced punishment to hold followers accountable for their ethical conduct. Despite the assume importance and prominence of ethical leadership among organizations, there are still many questions relating to its antecedents and consequences. One is whether the likelihood of an leading organization being perceived as an ethical leader among other following organizations in marketing channels can be predicted using its characteristics and inter-organizational relationship maintenance skills. Identifying trait and skill antecedents will aid in the development of strategies for selecting and developing ethical leaders and determining the best means to reinforce ethical behaviors. The purpose of this study is to investigate the effects of three categorized variables on ethical leadership of channel leader. To be concrete, this study develops a model of the antecedents of three conceptually distinct forms of channel leader characteristics, such as organizational traits, inter-organizational relationship maintenance strategies, and supplier management strategies, and tests the hypothesized differential effects on ethical leadership of marketing channel leaders. The reason why this study deals with discount store channel is that there is very strong inter-dependence between a discount store and its suppliers. Their strong inter-dependence makes their relationship as the relationship between a leader and suppliers and creates an atmosphere that leadership occur without difficulty. The research model is as follows. For the purpose of empirical testing, 295 respondents of suppliers of discount store channel in Korea were surveyed. The procedures included scale reliability, and discriminant and convergent validity were used to validate measures. Also, the reliability measurements traditionally employed, such as the Cronbach's alpha, were used. All the reliabilities were greater than .70. This study conducted confirmatory factor analyses to assess the validity of our measurements. All items loaded significantly on their respective constructs(with the lowest t-value being 15.2), providing support for convergent validity. We then examined composite reliability and average variance extracted(AVE). The composite reliability of each construct was greater than .70. The AVE of each construct was greater than .50. This study tested research model using Partial Least Square(PLS). The estimation of the structural equation model revealed an acceptable fit of the model to the data($r^2$=.851). Thus, This study concluded that the model fit was considered acceptable. The results of PLS are as follows. The results indicated that conscientiousness, openness, conflict management, social networks, training, fair reward had positive effects on ethical leadership of channel leaders. On the other hand, emotional insecure had negative effect and agreeableness, assurance, and inter-organizational communication had no significant effect on supply chain leadership.