• Communications for Statistical Applications and Methods
• /
• v.13 no.1
• /
• pp.113-123
• /
• 2006

Normal mixture model(NMM) frequently used to cluster genes on microarray gene expression data. In this paper some of component means of NMM are modelled by a linear regression model so that its design matrix presents the pattern between sample classes in microarray matrix. This modelling for the component means by given design matrices certainly has an advantage that we can lead the clusters that are previously designed. However, it suffers from 'overfitting' problem because in practice genes often are highly dimensional. This problem also arises when the NMM restricted by the linear model for component-means is fitted. To cope with this problem, in this paper, the use of the factor analyzer NMM restricted by linear model is proposed to cluster genes. Also several design matrices which are useful for clustering genes are provided.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.28 no.6
• /
• pp.830-841
• /
• 2004

The necessity to understand shopping orientation is increasing. Yet, there has been few research that investigated the conceptual structure of clothing shopping orientation[CSO]. Therefore, the purpose of this study is to develop the conceptual structure of CSO. For that purpose, both documentary and empirical researches were conducted. The documentary research was conducted to develop a theoretical structure model as a basis for exploring the conceptual structure of CSO. The empirical research was conducted to identify and modify the theoretical model so as to develop a conceptual structure model. The data was analyzed using confirmatory factor analysis, exploratory factor analysis, and Pearson's correlation analysis. As a result, a conceptual structure model of CSO was developed. The model consisted of three hierarchical levels of dimensions; upper-dimensions, middle-dimensions and lower-dimensions. The upper-dimensions were composed of 'economic', 'hedonic', and 'convenient' dimensions. Each upper-dimension consisted of middle-dimensions and lower-dimensions. Confirmatory factor analysis was executed to assess the fitness and cross validity of the structure model.

• Journal of the Korea Safety Management & Science
• /
• v.8 no.4
• /
• pp.63-89
• /
• 2006

Recently, the technology is getting to be the most important factor for companies, as the industry is changing fast. The uncertainty and complexity of technology valuation arc higher so that the technology concentrated companies need more developed and high performance technology. This paper reviews the methods of technology valuation for five categories that have been developed by valuation researchers, (1) research of technology diffusion and acceptance model, (2) research of technology valuation, (3) research of technology import and export factor, (4) research of technology valuation model, (5) research of technology transfer and market. And we propose a new technology valuation model using need(market), seed(technology) and deeds(management) factor by cross impact matrix. This model gives us the reference negotiation range for deciding the amount of royalty. I hope this paper induces more research on this field of technology valuation.

• Journal of Environmental Impact Assessment
• /
• v.14 no.4
• /
• pp.165-177
• /
• 2005

This study was carried out to offer the basic methodology of the system and model to objectively assess the natural ecosystem for environmentally friendly land conservation and present the alternative plan on establishing the environmental policy. The results of this study were as follows. We selected four assessment factors associated with biotic, abiotic, qualitative, and functional factors. Also, there were extracted fifty-six indicators including density, total nitrogen, hemeroby degree, and goods production. The assessment factor showed that biotic one was very important. The importance of indicators were analyzed that rare and endangered plant was important in biotic factor, in case of abiotic, qualitative, and functional factors, organic matter, landscape diversity, and conservation of ecosystem were greatly important. The results of factor analysis on the characteristics of indicators, classified biotic factor into six factors including a structural one, abiotic factor as a soil and physical one, qualitative factor as five ones including hierarchical one, and functional factor as public and conservational one. In the results of analysis on assessment model, R-square of biotic factor was 51.7%, those of abiotic, qualitative, and functional one were each 58.4%, 44.2%, and 39.3%, and statistical problem was no existence. In future, to develop the assessement model and methodology of sustainable natural ecosystem, we will have to achieve the integrated model and grouping by assessment factor.

• ALGAE
• /
• v.17 no.2
• /
• pp.105-115
• /
• 2002

Influences of vrious environmental factors on the eutrophication of Nakdong River were analyzed statistically using water samples collected from 1 January, 1999, to 30 September, 2001 at Namji area. The relationships between the concentration of chlorophyll α (eutrophication index) and environmental factors and were analyzed to develop a statistical model which can predict the status of eutrophication. The concentation of chlorophyll α ranged from 66.2 mg · $m^{-3}$ to 70.8 mg · $m^{-3}$ during dry winter season and the average concentration during this study period was 35.5 mg · $m^{-3}$ Namji area of Nakdong River was in the hypereutrohic stage in terms of water quality. Stephanodiscus sp. and Aulacoseria granulata var. angustissima were dominant species during the witnter to spring time and summer to autumn period, respectively. Based on the correlation analysis and the analysis of variance between chlorophyll α concentration and environmental factors, significantly high positive relationships were found in the order of BOD> pH> COD > KMnO₄ consumption > DO > conductivity > alkalinity. In contrast to these factors, significantly negrative relationships were found as in the order of $PO₄^{3-}-P$ >water level>the rate of Namgang-dam discharge > NH₃-N> the rate of Andong-dam discharge> the rate of Hapchoen-dam discharge. Based on the factors analysis of environmental factors on the concentration of chlorophyll α, we obtained five factors as follows. The first factor included water level, pH, turbiditiy, conductivity, alkalinity and the rate of Namgang-dam discharge. The second factor included water temperature DO, NH₄+-N, NO₃- -N. The third factor included KMnO₄ consumption COD and BOD. The fourth factor included the rate of Andong-dam discharge, the rate of Hapcheon-dam discharge, and the rate of Imha-dam discharge. The final factor included T-N T-P and $PO₄^{3-}-P$ > concentration. We derived two statistica models that can predict the occurrence of eutrophication based on the factors by factor analysis, using regression analysis. The first model is the stepwise regression model whose independent variables are the factors produced by factor analysis : chl α (mg · $m^{-3}$ = 42.923+(18.637 factor 3) + (-17.147 factor 1) + (-12.095 factor 5) + (-4.828 factor 4). The second model is the alternative stepwise regression model whose independent variables are the sums of the standardized main component variables:chl α (mg · $m^{-3}$ = 37.295+(7.326 Zfactor 3) + (-2.704 Zfactor 1)+(-2.341 Zfactor 5).

• Asian-Australasian Journal of Animal Sciences
• /
• v.10 no.2
• /
• pp.233-239
• /
• 1997

A mammary epithelial cell line (MAC-T) established as a model for lactation was utilized to identify and characterize effects of various hormones upon insulin-like growth factor binding protein secretion. Ligand and immunoblot analyses of conditioned media indicated that insulin-like growth factor binding protein-2 was secreted by MAC-T cells. Insulin-like growth factor-I stimulated insulin-like growth factor binding protein-2 secretion in a dose-dependent manner, but prolactin and bovine somatotropin did not alter insulin-like growth factor binding protein-2 secretion. Insulin increased and cortisol decreased insulin-like growth factor binding protein-2 secretion. Effects of insulin-like growth factor-I on insulin-like growth factor binding protein-2 secretion support previous studies using primary cultures of bovine mammary cells and bovine fibroblasts. Effects of cortisol and insulin on insulin-like growth factor binding protein-2 secretion may be explained by changes in protein synthesis. In addition, supraphysiological doses of insulin can cross-react with the insulin-like growth factor-I receptor and stimulate insulin-like growth factor binding protein-2 secretion. MAC-T cells provide a model system to study mechanisms that regulate local insulin-like growth factor-I bioactivity.

• Journal of Korean Elementary Science Education
• /
• v.36 no.3
• /
• pp.208-218
• /
• 2017

This study was to investigate factors and disclose causal model of the scientific literacy competency about the motivation for science and the scientific literacy competency. The 3 grade university students and the 1 grade university students as pre-service elementary teachers were participated to questionnaire investigation. The data were analyzed by the factor analysis method and the structural equation model method, and the following results were obtained. First, the 3 grade university students and the 1 grade university students perceived the science interest factors and science usefulness factors as the motivation for science, and also revealed the scientific problem recognition factor and the scientific evidence use factor as the scientific literacy competency. Second, the science interest factor had a greater effect on the scientific problem recognition factor than the scientific evidence use factor in both the 3 grade and 1 grade university students. In the path from the science usefulness factor to the scientific problem recognition factor, the science usefulness factor of the 3 grade university students had a greater influence on the direct route to the scientific problem recognition factor than that of the 1 grade university students. In the path from the science usefulness factor to the scientific evidence use factor, the science usefulness factor of the 1 grade university students influenced more on the direct route to the scientific evidence use factor than that of the 3 grade university students.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.2
• /
• pp.323-334
• /
• 2015

he current VaR model based on the J.P. Morgan's RiskMetrics structurally can not reflect the future economic situation. In this study, we propose a One-factor model resulting from the Wiener stochastic process decomposed into a systematic risk factor and an idiosyncratic risk factor. Therefore, we are able to perform a preemptive risk management by means of reflecting the predicted common risk factors in the model. Stocks in the portfolio are satisfied with the independence to each other because the common factors are fixed by the predicted value. Therefore, we can easily determine the investment in each stock to minimize the variance of the portfolio. In addition, the portfolio VaR is decomposed into the sum of the individual VaR. So we can effectively implement the constitution of the portfolio to meet the target maximum losses.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.235-245
• /
• 2012

Logistic discrimination is an useful statistical technique for quantitative analysis of financial service industry. Especially it is not only easy to be implemented, but also has good classification rate. Generalized additive model is useful for credit scoring since it has the same advantages of logistic discrimination as well as accounting ability for the nonlinear effects of the explanatory variables. It may, however, need too many additive terms in the model when the number of explanatory variables is very large and there may exist dependencies among the variables. Mixtures of factor analyzers can be used for dimension reduction of high-dimensional feature. This study proposes to use the low-dimensional factor scores of mixtures of factor analyzers as the new features in the generalized additive model. Its application is demonstrated in the classification of some real credit scoring data. The comparison of correct classification rates of competing techniques shows the superiority of the generalized additive model using factor scores.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.667-680
• /
• 2007

The bio-data processing is used for a suitable purpose with bio-signals, which are obtained from human individuals. Recently, there is increasing demand that the bio-data has been widely applied to various applications. However, it is often that the number of data within each class is limited and the number of classes is large due to the property of problem domain. Therefore, the conventional pattern recognition systems and classification methods are suffering form low generalization performance because the system using the lack of data is influenced by noises of that. To solve this problem, we propose a modified additive factor model for bio-data generation, with two factors; the class factor which affects properties of each individuals and the environment factor such as noises which affects all classes. We then develop a classification system through defining a new similarity function using the proposed model. The proposed method maximizes to use an information of the class classification. So, we can expect to obtain good generalization performances with robust noises from small number of datas for bio-data. Experimental results show that proposed method outperforms significantly conventional method with real bio-data.