• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.309-327
• /
• 2021

Dynamic treatment regimes (DTRs) are decision-making rules designed to provide personalized treatment to individuals in multi-stage randomized trials. Unlike classical methods, in which all individuals are prescribed the same type of treatment, DTRs prescribe patient-tailored treatments which take into account individual characteristics that may change over time. The Q-learning method, one of regression-based algorithms to figure out optimal treatment rules, becomes more popular as it can be easily implemented. However, the performance of the Q-learning algorithm heavily relies on the correct specification of the Q-function for response, especially in observational studies. In this article, we examine a number of double-robust weighted least-squares estimating methods for Q-learning in high-dimensional settings, where treatment models for propensity score and penalization for sparse estimation are also investigated. We further consider flexible ensemble machine learning methods for the treatment model to achieve double-robustness, so that optimal decision rule can be correctly estimated as long as at least one of the outcome model or treatment model is correct. Extensive simulation studies show that the proposed methods work well with practical sample sizes. The practical utility of the proposed methods is proven with real data example.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.441-452
• /
• 2013

This study analyzed the relationship between key film and a box office record success factors based on movies released in the first quarter of 2013 in Korea. An over-fitting problem can happen if there are too many explanatory variables inserted to regression model; in addition, there is a risk that the estimator is instable when there is multi-collinearity among the explanatory variables. For this reason, optimal variable selection based on high explanatory variables in box-office performance is of importance. Among the numerous ways to select variables, LASSO estimation applied by a generalized linear model has the smallest prediction error that can efficiently and quickly find variables with the highest explanatory power to box-office performance in order.

• Journal of Korean Society for Quality Management
• /
• v.40 no.4
• /
• pp.631-640
• /
• 2012

Purpose: This empirical study is focused on the relationship between innovation capability (R&D and Human Resource innovation) and performance in knowledge-based service firms. Methods: We build research model to test how each of innovation capability on technology and human resource is influenced on their financial and non-financial performance in the knowledge-based service industries. Based on the previous research, we hypothesized the factors are regarded innovation capabilities of the firms as the scale of R&D and human resources. Because this study is especially targeted to the performance of knowledge-based service firms. With the survey on 424 main knowledge-based service firms, the multi-regression analysis was performed. Results: The result showed that the scale of R&D and human resources capabilities are main factors for knowledge-based service firms' performance, which reflects the current industrial structure. Conclusion: This study empirically demonstrated that human resources are most important to the growth of knowledge-based service firms.

• Journal of the Korean Society of School Health
• /
• v.29 no.2
• /
• pp.107-115
• /
• 2016

Purpose: This study is a descriptive survey which attempts to understand family strength, parenting attitude, and the ego-identity perceived by female high school students and identify the factors influencing ego-identity of the students. Methods: Data collection was carried out through a questionnaire survey of 186 female high school students. The collected data were analyzed by descriptive statistics, t-test. ANOVA, correlation analysis, and multi-variate regression analysis while using SPSS 23.0 program. Results: Family strength and the ego-identity perceived by female high school students were at a mid-level, with an average of 207.76 and 149.72 points, respectively. Parenting attitude showed scores higher than the mid-level, recording 90.36 points in average. As a result of analyzing the correlation between the factors, the higher family strength and the ego-identity of female high school students were, the better were the patenting attitudes of perceived parents. Besides, family health, parenting attitude, and family form (nuclear family) were found to be the factors influencing ego-identity formation of female high school students with the explanatory power being 25.5% in total. Conclusion: Developing intervention programs which take into account family strength is considered necessary to help the youth form positive ego- identity.

• Research in Community and Public Health Nursing
• /
• v.24 no.2
• /
• pp.143-150
• /
• 2013

Purpose: This study was to investigate the relationship between self-esteem and satisfaction with volunteer work in a population of health care center volunteers. Ultimately, the results from this study would help to find ways to keep volunteers continuing their work. Methods: The participants of this study were 179 volunteers who were affiliated with three health care centers located in Gyeonggi-do. Descriptive statistics and multi-stage regression were conducted to analyze data. Results: Self-esteem was significantly associated with the satisfaction with volunteer activity. In addition, the relationship with clients rather than volunteers' general characteristics was also significantly related to the satisfaction with volunteer work. Conclusion: Therefore, it is necessary to increase a volunteer's self-esteem so that the volunteer can keep continuing his or her volunteering activities. Also, in order to promote good relationships between the volunteers and the clients, it will be important to teach communication skills to volunteers.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.1 s.108
• /
• pp.10-18
• /
• 2005

The main concept of social carrying capacity is based on the principle that 'there are limits to the number of users a given recreation site can accommodate in order to provide quality of recreation experience'. The quality of the experience is revealed as user's satisfaction and perceived crowding. In this respect, studies of social carrying capacity have been frequently conducted by measuring perceived crowding and satisfaction. The purpose of this study is to identify the variables affecting perceived crowding, and causality bet-ween satisfaction and perceived crowding. Four hundred seventy six visitors were selected at Naejangsan National park on peak day of autumn excursion through on-site survey. The collected data were applied by factor analysis for categorizing the research variables, and multiple regression for finding the causality among variables. The study results are follows. The expectation of crowding, as a normative variable for perceived crowding, are categorized by three factors; circulation, user facility, and landscape. The circulation factor is the most powerful affecting perceived crowding among three factor. The landscape factor, however, do not have statistical significance on perceived crowding. The causality between satisfaction and perceived crowding is found. Although this relation is significant in statistics, magnitude of the coefficient is very small. It might be interpreted that satisfaction cannot be predicted simply from a user's perception of crowding, but a multi-dimensional concept such as adaptation and coping behavior.

• Journal of Distribution Science
• /
• v.12 no.5
• /
• pp.27-32
• /
• 2014

Purpose - Since Iran's economy is only now developing, and its stock market is only now emerging, we should deal with the relationship between ownership structure and conservative accounting of companies to see whether such a relationship exists in Iran's market. This study aims to investigate the relationship between ownership structure and accounting conservatism of listed companies on the Tehran Stock Exchange. Research design, data, and methodology - All listed companies on the Tehran Stock Exchange, for which the required information financial statements (balance sheet, profit and loss account) could be acquired for the period 2007-2012, were studied. A total of 123 companies from various industries was selected. Results - In order to test the hypotheses, multi variate regression (inter procedure), with their meaningful t- and f-statistics, and a Durbin-Watson autocorrelation model were used. Conclusions - The research results show that the ownership of major shareholders and ownership concentration have a negative significant relationship with accounting conservatism. Therefore, as a significant negative relationship between concentration of ownership and accounting conservatism at the 95% confidence level was found, the second hypothesis was confirmed.

• Korean Journal of Occupational Health Nursing
• /
• v.25 no.3
• /
• pp.227-237
• /
• 2016

Purpose: The purpose of this study was to identify the effects of nursing work environment and job stress on health problems of hospital nurses. Methods: The subjects were 200 nurses working in S general hospital in Gyeongnam, and the data were collected using organized questionnaire from Jan 10 to 25, 2015. The Korean version of the practice environment scale of nursing work index, the instrument for job stress, and the Korean version of Todie Health Index for health problem were used for measurement. The collected data were analyzed using descriptive statistics, t-test, ANOVA, Pearson's correlation, and multiple regression. Results: The nursing work environment was found to be slightly negative, and the job stress was found to be high. There were significant correlation among nursing work environment, job stress, and health problems. In addition, it showed that the nursing work environment and job stress of nurses were factors affecting their health problems. Conclusion: The nursing work environment and job stress are influencing factors on the health problems of hospital nurses. Multi-faceted efforts to create a positive nursing work environment are required. Further researches related to association between the nursing work environment and health problem of nurses are needed.

• Journal of Family Resource Management and Policy Review
• /
• v.16 no.4
• /
• pp.213-233
• /
• 2012

This descriptive study about a community center for elderly users identifies factors influencing economic dependency. The objective of this study is to find factors that contribute to increased economic dependency and to provide basic data for preventing conflict between caregivers and elderly dependents. The subjects are 204 elderly persons who are community-center users in SongPa-Gu. Thirteen dongs (administrative areas) were chosen randomly in a cluster sample from among 26 dongs in Soungpagu containing a total of 158 community centers for the elderly. I obtained informed consents for my research from all subjects, and collected data by conducting interviews from June 28th, 2011 to August 7th, 2011. The data was analyzed by descriptive statistics, t-test, one-way ANOVA, Duncan test and multi regression analysis. The mean economic dependency score was 3.23, meaning that subjects with this score are dependent at a level that is "over intermediate". The level of formal education, homeownership, financial assistance from family and the number of families, financial assistance to the family and the number of families, economic life satisfaction, self efficacy and social support.

• Journal of Information Technology Applications and Management
• /
• v.21 no.2
• /
• pp.15-29
• /
• 2014

This study analyzes the influence factors of IPTV users on the purchase of paid contents. This study carries out a web-log analysis of the actual users of the service provided by the domestic IPTV providers and classifies the influence factors on the purchase of paid contents largely into VOC, switching barriers, and content consumption pattern to conduct an empirical analysis. As analysis procedure, first, this study analyzes the preceding researches related to the core influence factors and content-purchasing patterns, and second, conducts a basic statistics analysis of the distribution of basic characteristics of the logs used, as presented in the above. Third, this study carries out a multiple regression analysis as an estimating equation of the number of purchasing the paid content depending on switching barriers of IPTV service, VOC, and content consumption pattern. As a statistical package, Stata version 11.2 was used. Through the empirical analysis, this study found that of the service use logs, VOC and content consumption pattern had a multi-dimensional impact on the purchase of premium contents. On the other hand, this study also found that the impact of switching barriers such as combination state with other products and current status of holding a point did not have a significant impact on the purchase of paid contents.