• Journal of the Korean Statistical Society
• /
• v.24 no.2
• /
• pp.495-506
• /
• 1995

We present formula for detecting influential observations on the smoothing parameter in smoothing spline. Further, we express them as functions of basic building blocks such as residuals and leverage, and compare it with the local influence approach by Thomas (1991). An example based on a real data set is given.

• Journal of the Korean Statistical Society
• /
• v.16 no.1
• /
• pp.10-20
• /
• 1987

The value of statistics used for variable selection criteria can be reduced remarkably by excluding only a few influential cases. Furthermore, different subsets of regressors change leverage and influence patterns for the same response variable. Based on these motivations, this paper suggests a procedure which considers variable selection and detection of influential cases simultaneously.

• Journal of Fashion Business
• /
• v.8 no.3
• /
• pp.34-48
• /
• 2004

This study aims to determine any possible causation between identifying which major factors affect CRM(Customer Relationship Management) in terms of promotion strategies for fashion goods and classifying customers into several categories, so that it can seek reasonable strategic measures based on CRM. This study suggested a model by selecting several variables meeting its goals, and used total 672 sheets of questionnaire for final analysis. In addition, a structural equation model was analyzed As a result, it was found that pricing flexibility had more or less influential relationships with trust, satisfaction and commitment in CRM, although having a negative relationship with commitment. Salesperson's role was also significantly correlated with trust, satisfaction and commitment in CRM, and especially, there were more influential relationships with satisfaction than any other factor. Service quality had relatively high influential relationships with trust, satisfaction and commitment in CRM. Retained customers showed more or less influential relationships with trust, satisfaction and commitment, while loyal customers did so with satisfaction and commitment, except for trust.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.1
• /
• pp.19-26
• /
• 2015

Recently, a lot of users are using social network services as the spread of SNS and generalization of smart-phone. In this study, we apply clustering and ranking method for finding twitter influential users. First, we propose five ranking elements. The five elements include the number of follow, the number of retweet, IRP, IFP and influ-score. These elements are used by centroid point of clustering methods. This study can help to find novel approaches for finding twitter influential users.

• Journal of the Korean Statistical Society
• /
• v.29 no.3
• /
• pp.337-350
• /
• 2000

This paper suggests a new diagnostic measure and a stopping rule for detecting influential observations in multiple discriminant analysis (MDA). It is developed from a Bayesian point of view using a default Bayes factor obtained from the fractional Bayes factor methodology. The Bayes factor is taken as a discriminatory information in MDA. It is shown that the effect of an observation over the discriminatory information is fully explained by the diagnostic measure. Based on the measure, we suggest a stopping rule for detecting influential observations in a given training sample. As a tool for interpreting the measure a graphical method is sued. Performance of the method is used. Performance of the method is examined through two illustrative examples.

• The Korean Journal of Applied Statistics
• /
• v.6 no.1
• /
• pp.67-78
• /
• 1993

A new diagnostic statistic for detecting outliers and influential observations in linear models is suggested and studied in this paper. The proposed statistic is a weighted sum of two measures; one is for detecting outliers and the other is for detecting influential observations. The merit of this statistic is that it is possible to distinguish outliers from influential observations. We have done some Monte-Carlo Simulation to find the probability distribution of this statistic.

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.289-301
• /
• 1996

This paper suggests a new diagnostic measure for detecting influential observations in two group linear discriminant analysis(LDA). It is developed from an information theoretic point of view using the minimum discrimination information(MDI) methodology. MDI estimator of symmetric divergence by Kullback(l967) is taken as a measure of the power of discrimination in LDA. It is shown that the effect of an observation over the power of discrimination is fully explained by the diagnostic measure. Asymptotic distribution of the proposed measure is derived as a function of independent chi-squared and standard normal variables. By means of the distributions, a couple of methods are suggested for detecting the influential observations in LDA. Performance of the suggested methods are examined through a simulation study.

• Journal of the Korean Home Economics Association
• /
• v.37 no.3
• /
• pp.157-174
• /
• 1999

The purpose of this study is to investigate かe factors related to the environment-oriented consumer behavior, and to analyze the effects of environmental knowledge, perception of environmental problems, and environment-oriented attitude on the environment-oriented consumer behavior. The data used in this study were collected through questionnaires on 535 wives living in Cheju City. The data were analvzed by using SPSS WIN program. The summaries of this study are as follows. Using behaviors was influenced by age and family income, but buying and disposing behavior are not influenced by socio-economic variables of wives. Environmental knowledge only has effects on disposing behaviors, and environment-oriented attitude behavior has effects on buying, using, and disposing behavior. But the perception of environmental problems hasn't effects on them. Wives' environment-oriented behavior are more effected by environment-oriented attitude than perception of environmental problems. In buying behavior, environment-oriented attitude is the most influential factor, and the reference group is the second influential factor. But in disposing behavior, the reference group is the most influential factor, and environment-oriented attitude is かe second influential factor.

• The Korean Journal of Health Service Management
• /
• v.8 no.3
• /
• pp.49-61
• /
• 2014

Due to the rapid population's aging, the life span's expansion and social & cultural characteristics, the standards of age classes in senescence are changed. Thus, this study aimed to identify the influential factors on health care utilization in the elderly by age class, and targeted 2,937 adults in their ages over 55 years old from the Korea Health Panel's 2009 Yearly Integrated Data. This study investigated the target health care utilization in the elderly in relation with the gender, the education level, the health-care insurance type, the income, the current job state, the chronic disease. In order to analyze the influential factors on health care utilization in the elderly, the multiple linear regression analysis was conducted to the data. As the results from this study, Concerning the influential factors on the health care utilization, the income, the subjective health state, the chronic disease and the regularly meals for the young-old influenced. Concerning the influential factors on the health care utilization, the subjective health state for the old. Concerning the influential factors on the health care utilization, the subjective health state, the income for the older-old influenced. Concerning the influential factors on the health care utilization, the education level, the spouse, the economic activity and the drinking oldest-old influenced. Therefore, it will need to provide systemic health-care & medical services, to develop health-care & medical programs and the health-care & medical policies and to execute them according to the age classes in senescence.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.1
• /
• pp.87-96
• /
• 2013

Influence propagation is an important research issue in social networks. Influence propagation means that the status or the disposition of nodes get changed by new idea, information and gossip propagated by other nodes. Influenced nodes also make other nodes influenced across the network. The influence propagation problem based on 'word of mouth' referral is to find most influential nodes set in networks to maximize influence. In this paper, we study the influence measuring and finding most influential nodes set in Delay-Tolerant Networks. It is difficult to measure exact influential power in Delay-Tolerant networks where network topology is not stable due to the nodal mobility. In this paper, we propose a distributed scheme that each node constructs $k$-clique community structure and estimates local influential power in Delay-Tolerant Networks. Simulation results show that the influential nodes information estimated by proposed scheme is in agreement with a global view of influential nodes information.