• Communications for Statistical Applications and Methods
• /
• v.28 no.5
• /
• pp.553-562
• /
• 2021

Directional regression (DR; Li and Wang, 2007) is well-known as an exhaustive sufficient dimension reduction method, and performs well in complex regression models to have linear and nonlinear trends. However, the extension of DR is not well-done upto date, so we will extend DR to accommodate multivariate regression and large p-small n regression. We propose three versions of DR for multivariate regression and discuss how DR is applicable for the latter regression case. Numerical studies confirm that DR is robust to the number of clusters and the choice of hierarchical-clustering or pooled DR.

• Journal of the Korean Statistical Society
• /
• v.28 no.2
• /
• pp.167-182
• /
• 1999

This article is concerned with the selection of subsets of predictor variables to be included in building the binary response probit regression model. It is based on a Bayesian approach, intended to propose and develop a procedure that uses probabilistic considerations for selecting promising subsets. This procedure reformulates the probit regression setup in a hierarchical normal mixture model by introducing a set of hyperparameters that will be used to identify subset choices. The appropriate posterior probability of each subset of predictor variables is obtained through the Gibbs sampler, which samples indirectly from the multinomial posterior distribution on the set of possible subset choices. Thus, in this procedure, the most promising subset of predictors can be identified as the one with highest posterior probability. To highlight the merit of this procedure a couple of illustrative numerical examples are given.

• International Journal of Contents
• /
• v.13 no.3
• /
• pp.65-74
• /
• 2017

Women's menopause is a natural process that every woman must eventually experience, but changes in hormones before and after menopause can serve to produce life-threatening crises in some situations, with individual differences. Data for the study was elicited from 22,610 Korean women ranging in age from 45 to 55 years in the 2013 Korean Community Health Survey. Statistical analyses was performed using descriptive, t-test, ANOVA, and hierarchical regression analysis using SPSS IBM 20.0 version. Individual characteristics, lifestyle, history of chronic disease(s), psychological and environmental factors were included as independent and EQ5D weights of Koreans were used as dependent variables. The survey subjects consisted of a total 15,505(58.3%) in their 50s, 1,765 (66.5%) in middle and high school dropouts or graduates, 22,174 (83.3%) living in spouses and 10,534(39.6%) in wages. There was a significant difference in HRQOL among all independent variables except drinking and residential areas. Hierarchical regression analysis showed that age, smoking, obesity and other incidental disease factors (fall, angina, asthma, arthritis, osteoporosis, stroke) had a negative effect on HRQOL. The selected independent variables accounted for 22.7% of HRQOL. It is necessary to find a way to improve HRQOL of Korean perimenopausal women, focusing on the significant variables revealed by the study results.

• Journal of Fisheries and Marine Sciences Education
• /
• v.27 no.3
• /
• pp.644-655
• /
• 2015

This study was planned to examine the moderating effects of depression and anxiety and the relationship between online game addiction and adolescents' delinquency. Data were collected from children and youth's mental health advocacy research by National Youth Policy Institute. The subjects were 409 adolescents aged between 14 and 18. Correlational analysis and hierarchical regression analysis were conducted to test research hypotheses. Results of this study were as follows: first, online game addiction had a significant positive relations with adolescents' delinquency. Second, depression and anxiety were significant positive relations with each other. And depression and anxiety were significant positive relations with adolescents' delinquency. The result from hierarchical regression analysis showed that significant moderating effect of depression was found. But the result wasn't exhibited twithin hat the two-way interaction effects of depression. On the other hand, result from hierarchical regression analysis showed that significant moderating effect of anxiety wasn't found. In conclusion, this study proposed the need for counseling approach focused on 'depression' in order to reduce the adolescent's delinquency.

• Korean Business Review
• /
• v.22 no.2
• /
• pp.111-137
• /
• 2009

The purpose of this study is to examine the moderating effect of emotional intelligence in the relationship between transformational leadership and organizational citizenship behavior. To achieve this research purpose, theoretical and empirical studies related to transformational leadership, organizational citizenship behavior, and emotional intelligence were carried out simultaneously. A field survey was undertaken through questionnaire sampling a population of public organization in Chungchungnamdo. The established hypotheses related to transformational leadership, organizational citizenship behavior, and emotional intelligence were verified by the hierarchical regression analysis using SPSS. The result of this research are as followers : First, hypothesis1 proposed that emotional intelligence will be moderate the effect of charisma on organizational citizenship behavior. The hierarchical regression analysis revealed that moderation term was insignificant. The interaction term for charisma and emotional intelligence had a insignificant and positive relationship with organizational citizenship behavior. Therefore, hypothesis1 was not supported by the data. Second. hypothesis2 stated that emotional intelligence will be moderate the effects of inspirational motivation on organizational citizenship behavior. Hypothesis2 The result of the hierarchical regression analysis show a insignificant interaction between inspirational motivation and emotional intelligence on organizational citizenship behavior. Therefore, hypothesis2 was not supported by the data. Third, hypothesis3 stated that emotional intelligence will moderate the effect of intellectual stimulation on organizational citizenship behavior. The result of the hierarchical regression analysis show a significant interaction between intellectual stimulation and emotional intelligence on organizational citizenship behavior. Therefore, hypothesis3 was supported by the data. Fourth, hypothesis4 proposed that emotional intelligence will moderate effect of individualized consideration on organizational citizenship behavior. The hierarchical regression analysis revealed that the interaction term for individualized consideration and emotional intelligence had a significant and positive relationship with organizational citizenship behavior. Therefore, hypothesis4 was supported by the data. This study revealed that emotional intelligence moderate the relationship between intellectual stimulation, individualized consideration, and organizational citizenship behavior. It concludes that organizational citizenship behavior varies with coalignment of transformational leadership and emotional intelligence.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.695-704
• /
• 2020

Recently, There has been an increasing of utilization IT, and studies have been conducted on predicting learning results. In this study, Learning activity data were collected that could affect learning outcomes by using learning analysis. The survey was conducted at a university in South Chung-Cheong Province from October to December 2018, with 1,062 students taking part in the survey. First, A Hierarchical regression analysis was conducted by organizing a model of individual, academic, and behavioral factors for learning results to ensure the validity of predictors in machine learning. The model of hierarchical regression was significant, and the explanatory power (R²) was shown to increase step by step, so the variables injected were appropriate. In addition, The linear regression analysis method of machine learning was used to determine how predictable learning outcomes are, and its error rate was collected at about 8.4%.

• The Journal of the Korea Contents Association
• /
• v.22 no.3
• /
• pp.179-188
• /
• 2022

The purpose of this study is to analyze the variables affecting the institutional commitment of college students. Based on the relevant literature review, this study subdivided institutional commitment of college students into three; academic integration, social integration and institutional commitment. To achieve the goals, the hierarchical regression analysis was conducted using KELS(Korea Educational Longitudinal Survey) data collected by KEDI in 2018. Major findings are as follows: factors related to college experiences such as learning styles, negligence of learning, college climate, interaction with faculty members or peer group were found to be associated with the institutional commitment of college students. With regard to students' background, male students revealed lower level of academic integration and institutional commitment. The regression model disclosed that students from medicine demonstrated higher social integration compared to other majors. Based on the findings of the study, policy implications were discussed.

• Communications for Statistical Applications and Methods
• /
• v.3 no.3
• /
• pp.31-37
• /
• 1996

A hierarchical loglinear model comparison method is developed which is based on the well kmown partitioned likelihood ratio statistiss. For any paels, we can regard the difference of the geedness of fit statistics as the variation explained by a full model, and develop a partial test to compare a full model with a reduced model in that hierarchy. Note that this has similar arguments as that of the regression analysis.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.18 no.4
• /
• pp.452-462
• /
• 2011

Purpose: The purpose of this study was to examine the factors affecting body image among undergraduate students. Method: The research design for this study was a descriptive survey design using a convenience sampling. Data collection was done using self-report questionnaires with 319 undergraduate students located in 3 cities, Seoul, Gangneung and Seosan. Pearson correlation coefficients and hierarchical multiple regression with the SPSS Win 12.0 Program were used to analyze the data. Results: In the hierarchical multiple regression analysis, gender, height, weight and college major were controlled. Body surveillance and body shame significantly predicted 72.3% of appearance orientation. Sociocultural attitudes toward appearance and self-esteem significantly predicted 33.5% of appearance evaluation. Self-esteem and body surveillance significantly predicted 15.9% of health orientation. Self-esteem significantly predicted 23.3% of health evaluation. Conclusion: Findings from this study provide a comprehensive understanding of body image and related factors in undergraduate students in Korea. However, further study with a larger random sample and more a detailed research design is necessary.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.24 no.6
• /
• pp.928-939
• /
• 2000

This thesis will study the determinants of consumer satisfaction based on the disconfirmation theory. The proposed questions are first, to find out if desire and expectation are conceptually distinct. Second, to study the effects of desire, expectation, perceived performance, desire congruency, and expectation congruency on clothing satisfaction. The data used in this thesis were obtained from a two stage longitudinal survey. SPSS WIN 8.0 was used for the analysis and the following method such as mean, correlation, t-test, hierarchical regression were applied. The results indicate that first, according to the correlation analysis and crosstab analysis, satisfaction and desire were perceived as two different concepts. Second, using the hierarchical regression analysis to compare the effects of determinants of consumer satisfaction, the model of desire, expectation, performance, desires congruency, expectations congruency best explain the clothing satisfaction. Among them, effects of performance had the strongest impact. Expectation did not influence satisfaction but desire did.