• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.609-617
• /
• 2006

A new fuzzy c-regression algorithm for switching regression analysis is presented, which combines fuzzy c-means clustering and least squares support vector machine. This algorithm can detect outliers in switching regression models while yielding the simultaneous estimates of the associated parameters together with a fuzzy c-partitions of data. It can be employed for the model-free nonlinear regression which does not assume the underlying form of the regression function. We illustrate the new approach with some numerical examples that show how it can be used to fit switching regression models to almost all types of mixed data.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.11a
• /
• pp.683-694
• /
• 2011

This study analysed impact of service quality on customer satisfaction and loyalty in the take-out coffee shop. The switching barrier was also studied as a moderating effect. Particularly, this study focused on relationships between customer loyalty and switching barriers. A lot of previous studies interest only in customers satisfaction. This study also analysed relationships among service quality, customer satisfaction, switching barriers and brand loyalty. Eventually, service quality significantly affects customer satisfaction, moderating effects, brand loyalty and marketing performance. SERVQUAL model which was established by PZB (1988) was used as a service quality factors. The impact on customer satisfaction was analysed using multiple regression analysis. Simple regression analysis was used to find effects of customer satisfaction and customer loyalty. Additional factors of switching barriers was classified based on previous studies. Hierarchical multiple regression analysis was used to find factors of customer loyalty among switching barriers. In the result, we can find that the importance of tangibles, responsiveness in service quality factors and contract cost, search cost and continuous cost in moderating effects.

• 한국데이터정보과학회:학술대회논문집
• /
• 2005.10a
• /
• pp.161-169
• /
• 2005

In this paper we propose a fuzzy c-regression model based on weighted least squares support vector machine(LS-SVM), which can be used to detect outliers in the switching regression model while preserving simultaneous yielding the estimates of outputs together with a fuzzy c-partitions of data. It can be applied to the nonlinear regression which does not have an explicit form of the regression function. We illustrate the new algorithm with examples which indicate how it can be used to detect outliers and fit the mixed data to the nonlinear regression models.

• Journal of Korean Society for Quality Management
• /
• v.32 no.2
• /
• pp.109-131
• /
• 2004

This research tried to clarify the impact of service quality on the customer satisfaction, customer retention and switching barriers in the competitive structure between department store and discount store. We measured the level of service quality by using the methodology which had been adopted in the service quality research area. Using the internet survey method, we gathered data from 750 consumers of each industry. We used various analysis methods such as the regression analysis, t-test, and hierarchical regression analysis. The results reveal different patterns in the two sectors in the retail industry with respect to switching barriers. We conclude that switching barriers play an important role in consumer satisfaction and retention.

• The Korean Journal of Applied Statistics
• /
• v.2 no.2
• /
• pp.37-45
• /
• 1989

Switching regression models are commonly used for the statistical analysis of the disequilibrium models. In this paper wer show how switching regression models can be classified by the sample separation criterion and how they are related to the disequilibrium models. The problems in the estimation of the disequilibrium models ar discussed for the ones with both known sample separation and unknown sample separation.

• Journal of the Korea Society for Simulation
• /
• v.22 no.2
• /
• pp.85-91
• /
• 2013

Smart phones become essential goods for our life. As the technology are developing, and the market becomes saturated, it is important to understand the determinants affecting purchase of smart phones. In this paper, to understand these determinants factor analysis and binary logistics regression is used. Toward this, we first define the determinants into 3 categories: customer satisfaction, switching barrier, and switching attractiveness based on literature review. Furthermore, we develop 9 hypotheses to test with survey data using factor analysis and binary logistics regression. The results show that the six factors (data quality, price satisfaction, corporate image, the burden of new contract, attraction of devices and attraction of other competitors) are significant when customers buy smart phones.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.25 no.8
• /
• pp.1512-1523
• /
• 2001

The purposes of this study were to examine the effect of switching barrier perception on store loyalty in apparel product purchasing to classify the factors of switching barrier perception, and additionally ot identify differences of store loyalty and switching barrier perception according to demographic characteristics. The questionnaire was administered to 300 women shopped in a department store in Gwang-ju city during February 10-23, 2001. Data collected from 261 women were analyzed by using frequency, factor analysis, ANOVA, Duncan-test, regression analysis by SPSS for windows PC program. The results were as follows; 1. The consumer’s perceived switching barrier was composed of three factors; economic psychological, time factor. 2. There was significant difference in store loyalty according to consumer’s age, occupation, education level. and income. 3. There was significant differences in economic. time switching barrier perception according to consumers’age, occupation education level, and income. There was significant difference in psychological switching barrier perception according to consumers’ occupation education level, and income. 4. The swiching barrier perception significantly infulenced on the store loyalty.

• Journal of the Korean Home Economics Association
• /
• v.41 no.9
• /
• pp.93-103
• /
• 2003

The purpose of this study was to examine the relationships between shopping styles, promotion usage behaviors, and consequential switching behaviors. Specifically, it examined: 1) the effects of shopping styles on promotion usage and switching behaviors; and 2) the effects of promotion usage on switching behaviors. A total of 378 responses collected from a questionnaire survey were analyzed. Multiple regression analyses showed that loyalty, fashion prone, brand prone, brand prone, value prone, and hedonic shopping prone styles among the 7 shopping styles affected promotion usage behaviors, and brand prone, hedonic shopping prone, and price prone styles affected switching behaviors. Also, sales and sweepstakes among the 6 promotion usage behaviors affected switching behaviors.

• Economic Analysis
• /
• v.17 no.2
• /
• pp.56-89
• /
• 2011

The sensitivity of investment with respect to cash flow is positive in imperfect financial markets. Using a switching regression model, cash flow sensitivity of investments in chaebol firms and large firms appears to be higher. Also, investments are found to be more responsive to cash flow during monetary contraction periods. These findings imply that monetary policy works through a credit channel. Furthermore, it appears that monetary policy exerts distributional effects as well as aggregate effects on that firms are unevenly affected by monetary changes.

• Culinary science and hospitality research
• /
• v.16 no.2
• /
• pp.31-48
• /
• 2010

The purpose of this study was to examine the influence of food service web site users' functional recognition extent on switching behaviors. For this, a survey of web site users was carried out. As for analytic methods, frequency analysis was used to examine respondents' demographic features. In addition, simple regression analysis and multiple regression analysis were carried out used to look into the influence of functional recognition of food providers' web sites on switching behaviors. Study findings are as follows: all the functional variables such as entertainment, advertisement & public relations, communication and purchase decision-making function have significant influence on users' switching behaviors. When users' recognition extent of food providers' online web sites is high, their switching behavior is also high. In particular, the following clause have the greatest influence upon users' switching behaviors pattern. In the function of entertainment, (1) it is easy to search on web site; in the advertisement function, (2) the image of restaurant can easily be recognize; In the communication function, (3) the image of new products can be seen with ease; and in the purchase decision-making function, (4) web sites are easily accessible.