• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.889-902
• /
• 2013

Several goodness-of-fit test statistics have been proposed for a multinomial logit regression model; however, the properties of the proposed tests were not adequately studied. This paper evaluates three different goodness-of-fit tests using grouping strategies, proposed by Fagerland et al. (2008), Bull (1994), and Pigeon and Heyse (1999). In addition, Pearson (1900)'s method is also examined as a reference. Simulation studies were conducted to evaluate the four methods in terms of null distribution and power. A real data example is presented to illustrate the methods.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.589-602
• /
• 2008

This article studies on disability pensioners' characteristic with multinomial logit and logistic regression model. Seven factors are examined on whether each factor is reflected in degree of disability in the disability pension. By incorporating multinomial logit and logistic regression model, effectiveness and characteristic of the seven factors are investigated on the degree of disability. Result shows all the seven factors are significant on the degree of disability, while among the seven, five factors, age, sex, type of coverage, type of category, insured duration show a trend in degree of disability and the other two, cause of disability and class of standard monthly income are not effective on trend in degree of disability. Results from analyses might be useful for disability pension management.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.859-869
• /
• 2011

Interest has increased in academic research regarding key factors that drive box-office success as well as the ability to predict the box-office success of a movie from a commercial perspective. This study analyzed the relationship between key success factors of a movie and box office records based on movies released in 2010 in Korea. At the pre-production investment decision-making stage, the movie genre, motion picture rating, director power, and actor power were statistically significant. At the stage of distribution decision-making process after movie production, among other factors, the influence of star actors, number of screens, power of distributors, and social media turned out to be statistically significant. We verified movie success factors through the application of a Multinomial Logit Model that used the concept of choice probabilities. The Multinomial Logit Model resulted in a higher level of accuracy in predicting box-office success compared to the Artificial Neural Network and Discriminant Analysis.

• Journal of Digital Convergence
• /
• v.17 no.7
• /
• pp.167-177
• /
• 2019

Innovation of genomics technology has recently been extended to Direct To Consumer Genetic Test (DTC-GT) which consumers purchase without requesting the service on medical institutes. In 2016, Korea has introduced the DTC-GT but the market size is small comparing to global market. This study analyzes consumers' purchase intentions and purposes and their influential factors based on 2018 consumer survey. According to the results of binominal and multinominal logistic regression, knowledge after purchase, attitude on medical care benefit, health status are statistically significant on purchase intentions. Purchase purposes are different on age group and related on medical care rather than health care. These results imply that DTC-GT is needed to improve consumer satisfaction, re-purchase and effective care service. This paper is expected to contribute on strategic directions for the new DTC-GT product development.

• Korean Journal of Social Welfare
• /
• v.66 no.1
• /
• pp.251-276
• /
• 2014

This study scrutinizes the common sense in the field of disability employment that the bigger the size of a firm, the lower the employment rate of people with disabilities. This common sense has been established by conventional cross-tabulation and multiple regression analyses without taking into account possible interactions between the sizes of firms and the industries in which they operate. This study shows that the distribution of the disability employment rate violates the linearity and homoscedasticity assumptions of the OLS. In an effort to find models that explain the data better, this study fits the OLS model, the weighted linear regression model, and the multinomial logit model as well as the path analysis which is meant to examine the relationships between firm size and other variables relevant to disability employment. The result shows that, when an interaction term between firm size and industry is added to the model, firm size does not have any significant effect on disability employment rate for those firms with 100 or more regular employees, to the contrary of the findings of prior studies. It also demonstrates that other factors such as job setting, the extent of helpfulness of disability employment employers perceive, employers' care for disability, and employers' awareness of disability policies may matter more than does firm size. This study proposes that future research and policy implementation for disability employment should pay no less attention to industry and other factors mentioned above than to firm size.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.11
• /
• pp.2238-2249
• /
• 2015

The purpose of this study is to analyze the relations of innovation and productivity following the introduction of ICT and the effects in the process of innovative investments activity-innovation-productivity, not only by finding causes and effects. For this purpose we conducted surveys of SMEs classified into 7 categories by type of business. To put it concretely, this study was performed to find out the foactors which allow companies to secure competitiveness by enhancing of innovative measures through ICT, and to further analyze the political implications for the development of small and medium-size business by conducting an empirical analysis of the process, from the determination of innovative investments all the way through to production. Analysis model used CDM model using econometric methods such as multiple regression analysis and multinominal logit analysis to produce results. Also we established and analyzed models of innovation investment determinants, innovation determinants and productivity determinants to analyze specifically the relations between ICT and productivity.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.7 no.3
• /
• pp.181-190
• /
• 2012

After industrialization, the labor force participation rates of women, especially married women is drastically increasing. So, this study was designed to analyze the determinants of married women's employment status considered. For this, the determinants of married women's employment status were divided into individual-related, children-related, household-related and job-related variables to establish the research models. Based on this, the following results were drawn from a multinominal logistic regression analysis of the determinants of married women's employment status. First, an analysis of individual-related variable showed that married women had the employment status of labor wages with residence in the center of the city and high academic background. Second, an analysis of children-related variable showed that they had the employment status of labor wages with many their children and no their children under the age of six. Third, an analysis of household-related variable showed that they had the self-employment status of labor wages with nuclear family and few income earners of family members. Finally, an analysis of job-related variable showed that they had the employment status of labor wages when they got a job before they got married, their husband didn't get a job, and their husband worked in a professional field. As for findings stated above, as there was a difference in the determinants of married women's employment status, the ways for improvement in the married women's employment status would be suggested as follows. First, married women with young children have the low employment status, basically, requiring problem-solving ways for this because the housekeeping and child-rearing burden caused by marriage and childbirth are factors that continue to obstruct a job. For this, the flexible working hours system, which housekeeping and child-rearing can harmonize with economic activities like developed countries, needs to be activated. But the activation of such flexible working system will produce actual results under institutional protection, such as a related-protection law. Second, the Leave of Child Care System is debated as one of the most representatively systems that housekeeping can harmonize with economic activities. Now, although the System is legislated, the use is very poor.