• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.571-580
• /
• 2008

The logistic regression analysis is widely used in the area of customer relationship management and credit risk management. It is well known that the maximum likelihood estimation is not appropriate when multicollinearity exists among the regressors. Thus we propose the logistic principal components regression to deal with the multicollinearity problem. In particular, new method is suggested to select proper principal components. The selection method is based on the condition index instead of the eigenvalue. When a condition index is larger than the upper limit of cutoff value, principal component corresponding to the index is removed from the estimation. And hypothesis test is sequentially employed to eliminate the principal component when a condition index is between the upper limit and the lower limit. The limits are obtained by a linear model which is constructed on the basis of the conjoint analysis. The proposed method is evaluated by means of the variance of the estimates and the correct classification rate. The results indicate that the proposed method is superior to the existing method in terms of efficiency and goodness of fit.

• The Korean Journal of Applied Statistics
• /
• v.22 no.3
• /
• pp.531-539
• /
• 2009

Logistic regression is widely used as a datamining technique for the customer relationship management. The maximum likelihood estimator has highly inflated variance when multicollinearity exists among the regressors, and it is not robust against outliers. Thus we propose the robust principal components logistic regression to deal with both multicollinearity and outlier problem. A procedure is suggested for the selection of principal components, which is based on the condition index. When a condition index is larger than the cutoff value obtained from the model constructed on the basis of the conjoint analysis, the corresponding principal component is removed from the logistic model. In addition, we employ an algorithm for the robust estimation, which strives to dampen the effect of outliers by applying the appropriate weights and factors to the leverage points and vertical outliers identified by the V-mask type criterion. The Monte Carlo simulation results indicate that the proposed procedure yields higher rate of correct classification than the existing method.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.1
• /
• pp.151-159
• /
• 2012

This paper proposes to develop multi-currencies portfolio strategy using principal component analysis (PCA) and logistic regression (LR) in foreign exchange market. While there is a great deal of literature about the analysis of exchange market, there is relatively little work on developing trading strategies in foreign exchange markets. There are two objectives in this paper. The first objective is to suggest portfolio allocation method by applying PCA. The other objective is to determine market timing which is the strategy of making buy or sell decision using LR. The results of this study show that proposed model is useful trading strategy in foreign exchange market and can be desirable solution which gives lots of investors an important investment information.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.321-328
• /
• 2009

In regression analysis, the ordinary least squares estimates of regression coefficients become poor, when the correlations among predictor variables are high. This phenomenon, which is called multicollinearity, causes serious problems in actual data analysis. To overcome this multicollinearity, many methods have been proposed. Ridge regression, shrinkage estimators and methods based on principal component analysis (PCA) such as principal component regression (PCR) and latent root regression (LRR). In the last decade, many statisticians discussed sensitivity analysis (SA) in ordinary multiple regression and same topic in PCR, LRR and logistic principal component regression (LPCR). In those methods PCA plays important role. Many statisticians discussed SA in PCA and related multivariate methods. We introduce the method of PCR and LRR. We also introduce the methods of SA in PCR and LRR, and discuss the properties of SA in PCR and LRR.

• 한국체육학회지인문사회과학편
• /
• v.57 no.4
• /
• pp.387-394
• /
• 2018

The purpose of this study is to provide information regarding the strategies by identifying the main variables that determines the winning team based on the records of all games of the 2017 IIHF World Championship Top league. 64 matches were analyzed for the study. 6 variables were analyzed which included ratio of saves, shots on goal, penalties in minutes, time for power play, power play goals, and face off wins. Logistic regression analysis (LRA), multiple regression analysis (MRA), and principal component analysis (PCA) were implemented to examine the relationship between win and loss. In case of LRA, shots on goal (p<.001), face-off wins (p<.001) had significantly positive relation to winning of game whereas, penalties in minutes (p<.01) and time on power play (p<.01) had significantly negative. Using MRA, win percentage was calculated which had significant positive correlation to ratio of saves (p<.01) and face-off wins (p<.001) whereas, a significant negative with penalties in minutes (p<.001). For PCA, the winning team consisted of penalty, attack, and defense factors whereas, losing teams consisted only the attack and defense factors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.126-132
• /
• 2015

Technology forecasting is about understanding a status of a specific technology in the future, based on the current data of the technology. It is useful when planning technology management strategies. These days, it is common for countries, companies, and researchers to establish R&D directions and strategies by utilizing experts' opinions. However, this qualitative method of technology forecasting is costly and time consuming since it requires to collect a variety of opinions and analysis from many experts. In order to deal with these limitations, quantitative method of technology forecasting is being studied to secure objective forecast result and help R&D decision making process. This paper suggests a methodology of technology forecasting based on quantitative analysis. The methodology consists of data collection, principal component analysis, and technology forecasting by logistic regression, which is one of the data mining techniques. In this research, patent documents related to autonomous vehicle are collected. Then, the texts from patent documents are extracted by text mining technique to construct an appropriate form for analysis. After principal component analysis, logistic regression is performed by using principal component score. On the basis of this result, it is possible to analyze R&D development situation and technology forecasting.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.293-298
• /
• 2015

The vessel encounter data collected from the vessel trajectories in the maritime traffic situation is possible to analyze vessel collision and near-collision risk using statistical method. In this study, analyzing variables extracted from the vessel encounter data using factor analysis, we determine main factors effecting vessel collision risk from vessel encounter data. In order to calculate each factor, it used principal component analysis for factor analysis after normalization and standardization of vessel encounter variables. As a result of the factor analysis, main effect factors are summarized into the vessel approach factor and collision avoidance variance factor.

• The Korean Journal of Applied Statistics
• /
• v.32 no.3
• /
• pp.435-450
• /
• 2019

There is ample research on the Korea-China-Japan trilateral relationship in various directions that includes geopolitical aspects. There still exist escalated tensions in politics and diplomacy despite the remarkable growth in the economic and cultural exchanges between these countries. This study presents a way of representing national identity based on survey results via principal component analysis, and investigates if these national identities can be related to conflict and cooperation among the three countries. The results show that the attachment to the nation does not affect the conflicts between the countries and that a more friendly awareness of other countries tends to give a positive effect to cooperation between countries.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.207-209
• /
• 2022

In the IoT environment, it is possible to collect life pattern data by recognizing human physical activity from smart devices. In this paper, the proposed model consists of a prediction stage and a recommendation stage. The prediction stage predicts the scale of anxiety and depression by using logistic regression and k-nearest neighbor algorithm through machine learning on the dataset collected from life pattern data. In the recommendation step, if the symptoms of anxiety and depression are classified, the principal component analysis algorithm is applied to recommend food and light exercise that can improve them. It is expected that the proposed anxiety/depression prediction and food/exercise recommendations will have a ripple effect on improving the quality of life of individuals.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.25-39
• /
• 2017

Over 5 million people participate in cycle racing betting and its revenue is more than 2 trillion won. This study predicts the ranking of cycle racing using various statistical analyses and identifies important variables which have influence on ranking. We propose competitive ranking prediction models using various classification and regression methods. Our model can predict rankings with low misclassification rates most of the time. We found that the ranking increases as the grade of a racer decreases and as overall scores increase. Inversely, we can observe that the ranking decreases when the grade of a racer increases, race number four is given, and the ranking of the last race of a racer decreases. We also found that prediction accuracy can be improved when we use centered data per race instead of raw data. However, the real profit from the future data was not high when we applied our prediction model because our model can predict only low-return events well.