• 디지털융복합연구
• /
• 제13권10호
• /
• pp.121-133
• /
• 2015

본 튜토리얼은 R을 이용하여 공분산 기반의 구조방정식모델링을 수행하는 방법을 제시하고 있다. 이를 위해 본 튜토리얼에서는 기존 연구들에 대한 리뷰를 통해 공분산 기반의 구조방정식모델링을 위한 기준들을 정의하고, 하나의 예시 연구모형을 제시하여 공분산 기반의 구조방정식모델링을 지원하는 R 패키지인 "lavaan"을 이용하여 이 예시 모형을 분석하는 것을 보여준다. 결과물로 본 튜토리얼에서는 예시모형을 대상으로 한 R을 이용한 공분산 기반의 구조방정식모델링 기법과 실습 스크립트가 제시되었다. 본 튜토리얼은 공분산 기반의 구조방정식모델링을 처음 접하는 연구자들에게는 연구모형을 구조방정식 모델링으로 분석하는데 유용한 가이드가 될 것이며, 이미 공분산 기반의 구조방정식모델링에 익숙한 연구자들에게는 R을 이용한 새로운 공분산 기반의 구조방정식모델링 분석기법 제시를 통하여 R이라는 통합된 통계 소프트웨어 운영환경에서 심도 있는 연구를 위한 기반 지식을 제공할 것이다.

• 한국조사연구학회:학술대회논문집
• /
• 한국조사연구학회 2007년도 추계학술대회 발표논문집
• /
• pp.55-65
• /
• 2007

연구에서는 공분산구조분석을 실시하기 위해 주로 사용하고 있는 AMOS 소프트웨어에 대하여 알아보려고 한다. 응용소프트웨어에서 활용된 수학적인 모형을 알지 못하면, 구조방정식에 대한 충분한 이해를 할 수 없으며, 구조방정식에 대한 8가지 가정이 어떻게 구현되는지 알 수 가 없다. 따라서 본 연구에서는 구조방정식모형 연구에서 주로 활용되었던 LISREL 프로그램으로 RAM과 MOSAN을 구현하였고 AMOS 결과와 비교분석하였다. 연구 결과에 따르면 AMOS프로그램은 8가지의 모든 가정을 따르지 않는 것으로 나타났다. AMOS 프로그램이 MOSAN보다는 RAM으로 구현되고 있음을 본 연구를 통해 알 수 있다. AMOS 소프트웨어 프로그램은 잠재변수(F)와 측정오차(e)간의 상관값을 산출할 때 충분히 추정을 하지 못하고 부분적으로만 추정하여 값을 산출하고 있음을 알 수 있었다.

• 여성건강간호학회지
• /
• 제7권2호
• /
• pp.141-156
• /
• 2001

The purpose of this study was to develop and test the structural model of a contraceptive behavior in Married Korean women. A hypothesis model was constructed on the basis of the health belief model, the theory of planned behavior and extensive literature review of contraception. The model was built by seven constructs. Four exogeneous variables included in the model were consisted of the contraceptive knowledges, the perceived threats, the sexual autonomy and the communication within a couple. Four endogenous variables were consisted of the attitudes toward contraception, the perceived control, the ability to plan a intercourse and the contraceptive behaviors. Empirical data for testing the hypothetical model were collected by the self report questionnaires from 243 Korean married women. The questionnaires used in this study were developed by this researcher and their Cronbach's alpha scores were ranged from .60 to .88. The collected data were analyzed by SPSS program(ver. 8.0) for descriptive statistical analysis and LISREL program(ver. 8.12a) for covariance structural analysis. On the basis of this results, it could be suggested that contraceptive behaviors be greatly affected by the perceived threats, the communications within couple, the attitudes toward contraception and the perceived control. Finally this model would be useful for the practice, theory and research of nursing.

• 대한간호학회지
• /
• 제40권3호
• /
• pp.389-399
• /
• 2010

Purpose: The aim of this study was to construct a structural equation model that would further explain the mental health status of Korean immigrants living in Canada. Methods: Survey using a structured questionnaire was conducted with 386 people in Canada (Vancouver and Toronto). Six instruments were used in this model. The analysis of data was done with both SPSS 14.0 for descriptive statistics and AMOS 5.0 for covariance structure analysis. Results: Based on the constructed model, physical health status, immigrant life stress, self esteem, and quality of life were found to have significant direct effect on mental health. In addition, factors such as physical health status, immigrant life stress, quality of life, English proficiency, family cohesion and social support were found to indirectly affect mental health. The final modified model yielded Chi-square=34.79 (p<.001), df=13, $x^2$/df=2.68, GFI=0.98, AGFI=0.94, NFI=0.95, PNFI=0.44, PGFI=0.35, RMSE=0.07 and exhibited good fit indices. Conclusion: This structural equation model is a comprehensive theoretical model that explains the related factors and their relationship with mental health in Korean immigrants. Findings of this study can contribute to the designing of an appropriate prevention strategy to further improve the mental health of immigrants in Canada.

• 대한가정학회지
• /
• 제44권11호
• /
• pp.117-131
• /
• 2006

The purpose of this study was to verify a Structural Equation Model that constructed the causations among the structural leisure constraints, interpersonal leisure constraints, intrapersonal leisure constraints, leisure motivation, leisure activity participation, leisure satisfaction and the quality of life from the ecological perspective. The respondents were 301 elderly people residing in 4 free institutionalized elderly homes in Seoul. The data were analyzed by confirmatory factor analysis and covariance structure analysis using USREL 8.0 ver. The major results are summarized as follows: 1) Statistically, a goodness of fit is good of structural equation model presented in the study. 2) The structural leisure constraints and the interpersonal leisure constraints are some types of leisure environment of the aged in public homes from the ecological perspective. Such constraints would inevitably lead to a direct effect on individual leisure life and leisure motivation. 3) The important valuable factor which affected the leisure satisfaction and the quality of life in the elderly was the leisure motivation.

• Structural Engineering and Mechanics
• /
• 제28권2호
• /
• pp.129-152
• /
• 2008

This paper considers the solution of the stochastic differential equations (SDEs) with random operator and/or random excitation using the spectral SFEM. The random system parameters (involved in the operator) and the random excitations are modeled as second order stochastic processes defined only by their means and covariance functions. All random fields dealt with in this paper are continuous and do not have known explicit forms dependent on the spatial dimension. This fact makes the usage of the finite element (FE) analysis be difficult. Relying on the spectral properties of the covariance function, the Karhunen-Loeve expansion is used to represent these processes to overcome this difficulty. Then, a spectral approximation for the stochastic response (solution) of the SDE is obtained based on the implementation of the concept of generalized inverse defined by the Neumann expansion. This leads to an explicit expression for the solution process as a multivariate polynomial functional of a set of uncorrelated random variables that enables us to compute the statistical moments of the solution vector. To check the validity of this method, two applications are introduced which are, randomly loaded simply supported reinforced concrete beam and reinforced concrete cantilever beam with random bending rigidity. Finally, a more general application, randomly loaded simply supported reinforced concrete beam with random bending rigidity, is presented to illustrate the method.

• 한국식생활문화학회지
• /
• 제23권3호
• /
• pp.301-307
• /
• 2008

The purpose of this study was to assess the causal relationships among belief, subjective norm, moral feeling, attitude, and the intention to consume organic beef. A total of 326 questionnaires were completed by adult in Jeonnam area. Structural equation modeling was used to measure the causal relationships among the constructs. The structural analysis results indicated an excellent model-data fit. The covariance effects of belief and subjective norm, and belief and moral feeling were statistically significant. The effects of belief and moral feeling on attitude and intention to consume were also statistically significant. As expected, attitude had significant effects on intention to consume. Moreover, attitude played a mediating roles in the relationship between belief and intention to consume. Finally, based on structural analysis, a model was proposed for the interrelations among belief, subjective norm and moral feeling towards organic food, attitude and intention to consume. It should be noted that the original organic food consumption model was modified, and should preferably be validated by future research. Other constructs, such as perceived behavior control and consumption, may be incorporated to form models that consist of new antecedent and consequence pairs.

• 한국과학교육학회지
• /
• 제17권1호
• /
• pp.1-10
• /
• 1997

The purpose of this study was to analyze the structural model of causal effects of students' variables on science process skills. Student characteristics investigated in the study included attitude related to the science, logical thinking ability, scientific experiences, cognitive style. Covariance structural modeling procedures were used to test causal inferences about hypothesized relationships. The sample consisted of 319 6th grade students and 321 8th grade students in Seoul City, Korea. Five instruments were used in the study, TSPS(test of science process skills), GALT(group assessment of logical thinking), CEFT(children embedded figures test), questionnaire of attitude related to the science, questionnaire of scientific experience. For statistical analysis, the study adopted the structural equation modeling with LlSREL, a computer statistical program developed by J reskog and S rbom. Major findings of the study are as follows:1) Logical thinking ability has a most strong direct effect on science process skills. 2) The structural coefficient of scientific experience influence on attitude related to the science has the greatest direct one than the others in the covariance structural model. According to the results of this study, it is very importance that various scientific experiences, particularly hands-on activity, should be offer to students to improve science process skills. Also, understanding the relationships of student variable to science process skills will be helpful to decision making on the part of curriculum developers, science teachers and researchers.

• 유통과학연구
• /
• 제20권6호
• /
• pp.75-86
• /
• 2022

Purpose: This research aims to provide empirical evidence on the impact of digital literacy on behavioural intention regarding using technology for distribution of higher education. Design, Methodology, and Approach: Quantitative analysis was carried out using Covariance-Based Structural Equation Model with data collected from 901 students who fully experienced 2-year study online at different universities in Vietnam. The structural model was built with digital literacy as the primary indicator and other variables were included based on modified version of Unified Theory of Acceptance and Use of Technology (UTAUT2) by adopting performance expectancy, effort expectancy, social influence, habit, and hedonic motivation variables specifically for education sector. Self-efficacy was added to eliminate possible bias in technology acceptance. Results: From the results of model estimation, digital literacy presented positive impact on the online distribution of higher education in Vietnam. The mediating effects of various indicators such as performance expectancy, effort expectancy, social influence, habit, hedonic motivation, and self-efficacy are significantly determined by research model. Conclusion: The higher level of digital literacy of the students, the more likely that they will use technology in higher education study, especially online learning. Additionally, the mediating effects of indicators from the UTAUT2 theoretical model were also evident to be positively significant.

• 유통과학연구
• /
• 제22권4호
• /
• pp.1-10
• /
• 2024

Purpose: This study is aimed to introduce the application of phantom approach with structural equation modelling method for online learning. By integrating these innovative methodologies, the research seeks to advance the understanding of how the phantom approach can effectively complement and augment structural equation modeling techniques. Research design, data and methodology: A theoretical framework of Technology Acceptance Model (TAM) was modified and updated. A questionnaire was developed and used to extract information from 189 instructors who used online learning as their primary medium. The Covariance Based Structural Equation Modelling (CBSEM) was applied to test the direct effects and the phantom approach is used to handle the 2 mediators in the model. Results:social influence, perceived usefulness, and perceived ease of use exerted discernible impacts on instructors' intentionsto engage in online learning. These findings illuminate the intricate dynamics influencing instructor behavior within the realm of online education, underscoring the significance of various factors in shaping their intentions. Conclusions: In additions, the perceived usefulness and perceived ease of use had mediated the effect of social influence and instructor intention using phantom approach. Therefore, one can have concluded that this modified model was also confirmed, thereby reinforcing distribution strategies to online learning and overall education presence.