• Journal of Preventive Medicine and Public Health
• /
• v.56 no.4
• /
• pp.303-311
• /
• 2023

Traditional mediation analysis, which relies on linear regression models, has faced criticism due to its limited suitability for cases involving different types of variables and complex covariates, such as interactions. This can result in unclear definitions of direct and indirect effects. As an alternative, causal mediation analysis using the counterfactual framework has been introduced to provide clearer definitions of direct and indirect effects while allowing for more flexible modeling methods. However, the conceptual understanding of this approach based on the counterfactual framework remains challenging for applied researchers. To address this issue, the present article was written to highlight and illustrate the definitions of causal estimands, including controlled direct effect, natural direct effect, and natural indirect effect, based on the key concept of nested counterfactuals. Furthermore, we recommend using 2 R packages, 'medflex' and 'mediation', to perform causal mediation analysis and provide public health examples. The article also offers caveats and guidelines for accurate interpretation of the results.

• Knowledge Management Research
• /
• v.20 no.2
• /
• pp.1-24
• /
• 2019

This tutorial introduces procedures and methods for performing structural equation modeling using R. To do this, we present advanced analysis methods based on structural equation model such as mediation effect analysis, moderation effect analysis, moderated mediation effect analysis, and multiple-group analysis with R program code using R lavaan package that supports structural equation modeling. R is flexible and scalable, unlike traditional commercial statistical packages. Therefore, new analytical techniques are likely to be implemented ahead of any other statistical package. From this point of view, R will be a very appropriate choice for applying new analytical techniques or advanced techniques that researchers need. Considering that various studies in the social sciences are applying structural equations modeling techniques and increasing interest in open source R, this tutorial is expected to be useful for researchers who are looking for alternatives to existing commercial statistical packages.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.669-684
• /
• 2017

Mediation models are widely used in many fields of research and have recently gained attention in epidemiology. The mediation proportion is a standard measure to evaluate what part of the total exposure effect on an outcome may be explained by a particular mediator and to examine how important that pathway is relative to the overall exposure effect. A common question is how large a sample size is needed to achieve high statistical power or, equivalently, what magnitude of effect can be detected. Current power and sample size calculations for mediation analysis are limited and additional research is needed. We therefore propose a computer-intensive power analysis using the mediation proportion. We conduct simulation studies to calculate statistical powers and sample sizes. And then, we illustrate our power analysis using an example from the Adult Health Study of atomic-bomb survivors and demonstrate that the method is relatively straightforward to understand and compute.

• Journal of the Korean Society of Safety
• /
• v.39 no.1
• /
• pp.114-122
• /
• 2024

This study aimed to identify the multiple mediation effects of job satisfaction and job commitment on the relationships between job stress and workers' safety behavior in terms of compliance and participation, in which the multiple mediation effects are a hybrid of parallel and serial mediating relationships. The multiple mediation model was analyzed using the bootstrapping method through the PROCESS macro tool in SPSS. The results showed that job stress negatively affects job satisfaction, job commitment, and workers' safety behavior, and the relationship between job stress and safety behavior is mediated by both job satisfaction and job commitment. The serial mediation effects of job satisfaction and job commitment were also found to be statistically significant in the regression relationship between job stress and safety behavior. Further analysis of the compliance and participation subdimensions of safety behavior showed similar results. Specifically, the serial mediation effects of job satisfaction and job commitment on participation and compliance behavior were further supported; however, the mediation effect of job satisfaction was not significant, whereas that of job commitment did remain significant. Further research is needed to determine if the mediation effect of job satisfaction found in this study can be extended and generalized to workers in various fields and industries.

• Journal of Engineering Education Research
• /
• v.22 no.3
• /
• pp.32-40
• /
• 2019

This paper deals with the effects of teamwork competence on problem solving ability through the mediating effect of creative personality for the engineering students. For this purpose, a regression-based statistical mediation analysis has been performed for a simple mediation model in which teamwork competence and problem solving ability were treated as independent and dependent variables respectively, and creative personality was included as a mediation variable. The analysis results showed that the teamwork competence has direct effect on the problem solving ability as well as indirect effect through the creative personality. This result implies that the problem solving ability can be improved directly by improving the teamwork competence, and moreover, it can be further improved indirectly or through the mediation effect by improving the creative personality. Thus, in order to develop excellent problem solving ability, it is necessary to form team members in a balanced way between teamwork competence and creative personality in the team-based learning.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.48 no.2
• /
• pp.350-366
• /
• 2024

This study aimed to clarify the continuance intention of users of size recommendation services. The expectation-confirmation model framed the analysis of the 180 data points collected. The analysis determined the mediating effects of perceived usefulness and satisfaction on the relationship between expectation-confirmation and continuance intention. The moderated mediation effect of familiarity was also analyzed, and a path analysis was conducted using PROCESS macro. Results showed that expectation-confirmation had a significant effect on perceived usefulness, satisfaction, and continuance intention. Findings indicated that perceived usefulness affected satisfaction and continuance intention and confirmed that satisfaction affected continuance intention. In the relationship between expectation-confirmation and continuance intention, mediation analysis verified the mediation and double mediation of perceived usefulness and satisfaction. In the group with an above-average familiarity value, moderation analysis confirmed a moderating effect between perceived usefulness and satisfaction. Above-average familiarity values also confirmed that the moderating effect on continuance intention was significant.

• Human Ecology Research
• /
• v.54 no.3
• /
• pp.293-305
• /
• 2016

This study examines the mediation effect of teacher-child interactions in the process of the impact of teacher's teaching-efficacy on childhood education institutions and classroom environment on peer-play interactions. We used data from 970 children aged between 49 and 55 months and 970 homeroom teachers from the fifth Korean Child Panel (2012) of the Korea Institute of Child Care and Education. The model fitness was excellent after data were statistically analyzed with model of structure to testify the relationship and effect among teaching efficacy, classroom environment, teacher-child interactions, and peer-play interactions. First, the analysis also showed that the teacher's teaching efficacy did not influence peer-play interactions directly, but gave an indirect effect on the peer-play interactions with the mediation of the teacher-child interactions. Second, the classroom environment directly and indirectly influenced the peer-play interactions with the mediation of the teacher-child interactions. Third, the variable of teacher-child interactions was fully effective as a mediating variable in the process of the teaching efficacy and classroom environment influence on teacher-child interactions. Teaching efficacy and classroom environment influenced the peer-play interactions through the mediation of the teacher-child interactions. The significance of mediation effect of the teacher-child interactions was verified through a bootstrapping method.

• Journal of Engineering Education Research
• /
• v.23 no.6
• /
• pp.17-26
• /
• 2020

In this paper, the effect of daily creativity of engineering students on problem-solving ability is addressed through the dual mediating effect of teamwork competency and self-directed learning ability. To this end, a regression-based statistical mediation analysis has been performed on the dual mediation model in which daily creativity and problem solving ability were treated as independent and dependent variables respectively, and teamwork competence and self-directed learning ability were included as mediation variables. The analysis result confirmed that the daily creativity has direct effect on the problem-solving ability, as well as indirect effects through teamwork competence and self-directed learning ability. In particular, the serial mediating effect of teamwork competency and self-directed learning ability was also confirmed to be statistically significant in the relationship between daily creativity and problem-solving ability. This verifies that problem-solving ability can be improved not only directly by improving daily creativity but also indirectly by improving teamwork competence and self-directed learning ability. In addition, teamwork competency showed greater indirect effect on problem-solving ability than self-directed learning ability, so increasing teamwork competency has a more significant effect on improving problem-solving ability than increasing self-directed learning ability. Therefore, in order to develop better problem-solving ability, it is necessary to identify and improve the learners' teamwork competency first and to strive to create an environment where learners can solve problems based on mutual trust with their teammates.

• Asia-Pacific Journal of Business
• /
• v.15 no.1
• /
• pp.159-177
• /
• 2024

Purpose - The purpose of this study is to reveal the effect of a High Performance Work System(HWPS) on research performance. In addition, this study examines the mediation effect of Innovation Commitment(IC) and the moderated mediation effect of Perceived Organizational Support(POS), and seeks to reveal the antecedents and boundary variables that affect research performance. Design/methodology/approach - The level of analysis is at the individual level. A survey was collected from researchers at government-funded research institutes in the Daejeon and Sejong areas. 265 questionnaires were used in the final statistical analysis. Confirmatory factor analysis was performed using the AMOS 21. Correlation analysis, regression analysis, and bootstrapping by Process Macro were performed using the SPSS 19. Findings - As a result of the study, HWPS has a positive effect on IC, and IC has a positive effect on research performance. Through this results, it was found that IC mediates the relationship between the HPWS and research performance. In addition, POS positively moderated the mediating effect of HPWS on research performance through IC. Research implications or Originality - First, IC can be increased through a HPWS. Second, the effect of the HWPS on individual research performance through IC provides implications that the HWPS can be effectively applied not only to general companies but also to research organizations. Third, the boundary effect of POS was revealed. Fourth, research performance was measured through objective quantitative indicators rather than subjective.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.3
• /
• pp.221-228
• /
• 2018

This study aimed to analyze the impact of the motives of college students for choosing majors on career decision-making with self-efficacy used as a mediation effect, and to utilize the results as data for career counseling for college students. To do so, a research survey was conducted from November 1, 2017 to November 30, 2017, and based on the non-random convenience sampling technique, questionnaires were distributed to 1,300 students (2nd, 3rd, and 4th-year students) of five 4-year universities located in G Province. For frequency analysis and hypothesis testing, a multiple regression analysis and 3-step mediation effect analysis were used and the results of the analyses were as follows. The results of the analysis of the mediation effect of career self-efficacy on the impact of intrinsic motive on planning style showed that goal selection had a complete mediation effect. Given these results, it is necessary that educational institutions and society provide students, even during middle and high school years, with opportunities to discover their aptitudes and interests, and an educational system should be established to pave the way for students to be well prepared for and make decisions about the work they will do.