An Introduction to Confirmatory Factor Analysis (CFA) and Structural Equation Modeling (SEM): Investigating linear relationships among latent constructs

Purpose This study aims to find evidence of a possible relationship between three constructs that are generally investigated separately: entrepreneurial orientation, understood as entrepreneurship on the organizational level; marketing capability, seen as a highly competitive factor for the organization; and business performance, highlighted as a focus of the entire organization. Design/methodology/approach A survey-based quantitative approach was adopted with a cross-sectional temporal perspective. To arrive at results that can be compared, the study uses factor analysis and structural equations modeling techniques, with estimations of maximum likelihood for testing the quality of fit of the measures to the structural models, using SPSS 21 and AMOS 16 software. Data were collected at the 27th EXPOSUPER, which is a trade fair at which 35,000 visitors were present. The data collection instrument used is a questionnaire previously validated by Reis Neto et al. (2013a). The first section covers control variables chosen to profile the firms, the second contains entrepreneurial orientation variables, the third comprises marketing capability variables and the fourth section contains business performance variables, all using seven-point Likert response scales. Findings Tests of the entrepreneurial orientation measurement scale produced interesting results in this application within the retail supermarket industry. The results of exploratory factor analysis indicated that a scale with three dimensions was significant. The relationship between entrepreneurial orientation and marketing capability (H1) is positive, through the intermediate dimensions of innovation, proactiveness and risk-taking, used by firms’ management, contributing to their efforts to research and manage the market, to develop products and services and to offer better prices. Exploratory factor analysis and confirmatory factor analysis showed that four of the scale’s dimensions of the marketing capability were significant: market research, market management, new product development and pricing. Comparison of these results with those of Reis Neto et al. (2013a) reveals a difference, as although their result, achieved using structural equations modeling, also had four factors; the promotion dimension was the most significant and absorbed the other variables. Despite these differences, confirmatory factor analysis and structural equations modeling demonstrated that this construct met the minimum conditions for adequacy, where (H2), formulated to test the relationship between the marketing capability construct, was confirmed. The final construct analyzed in this study was business performance, initially suggested by González-Benito et al. (2009), and also used by Reis Neto et al. (2013a). They used the dimensions profitability, market value and market response, and in the present study, after exploratory factor analysis, confirmatory factor analysis and structural equations modeling, the results were identical to those authors results, in that (H3), formulated with the objective of testing the relationship between the entrepreneurial orientation construct and business performance, was confirmed, and although this was not the most robust of the relationships postulated in the three hypotheses, but was of lower significance. Research limitations/implications Although this study has achieved its objective, one of the study’s limitations relates to the data collection instrument, which was subject to failures in terms of the number of variables to be analyzed in each dimension. This led to elimination of certain dimensions during the analyses. Another limitation is related to the method used in the study. When questionnaires are used as data collection instruments, respondents often may not understand the true meaning of questions, which could lead them to choose any option, thereby stripping the results of credibility. In view of this limitation, it is suggested that future researchers conduct qualitative studies, using the case study method, which could offer greater clarity and increase understanding of the results related to these subjects. Even considering that this study has certain limitations and restrictions affecting generalization, it is hoped that it raises new questions, interests and inspirations, improving and complementing understanding of this strong social and economic sector. Originality/value It is identify the relationship between entrepreneurial orientation and marketing capability, since to date there is no evidence from studies confirming the existence of such a relationship. This statement was based on the results of a bibliographic survey conducted using the ProKnow-C, knowledge development process-constructivist methodology, in which, this originality was positive and significant, offering new studies from this point of view.

Although there have been some studies on the success factors for IT software projects, there is still a lack of coherent research on the success factors for IT service projects. Therefore, this study aimed to identify and understand the factors and their relationships that contribute to the success of IT service projects. For this purpose, multivariate regressions and structural equation models (SEMs) were developed and analyzed. The regression models included six project management success criteria used as dependent variables (quality of the delivered product, scope realization and requirements, timeliness of delivery, delivery within budget, customer satisfaction, and provider satisfaction) and four independent variables (agile techniques and change management, organization and people, stakeholders and risk analysis, work environment), which had been identified through exploratory factor analysis. The results showed that not all success factors were relevant to all success criteria, and there were differences in their importance. An additional series of exploratory and confirmatory factor analyses along with appropriate statistical measures were employed to evaluate the quality of these four factors. The SEM approach was based on five latent constructs with a total of twenty components. The study suggests that investing in improving people’s knowledge and skills, using agile methodologies, creating a supportive work environment, and involving stakeholders in regular risk analysis are important for project management success. The results also suggest that the success factors for IT service projects depend on both traditional and agile approaches. The study extensively compared its findings with similar research and discussed common issues and differences in both the model structures and methodologies applied. The investigation utilized mathematical methods and techniques that are not commonly applied in the field of project management success modeling. The comprehensive methodology that was applied may be helpful to other researchers who are interested in this topic.

The purpose of this study was (a)to clearly define the concept of service quality as it relates to the online sports shopping mall, and (b)to develop and validate a psychometrically sound measurement scale, (c)examine the relationship among service quality and shopping satisfaction and intention of recommendation for marketing strategy internet sport shopping mall management. Following Churchill’s(1979) suggestions, the author developed internet Sports Shopping Mall Service Quality(E-SSMSQ). For the development E-SSMSQ (1)literature review, (2)focus group interview, (3)in-depth interviews (4)pilot test(n=97), (5)first data collected(n=459), (6)Frequency analysis, descriptive analysis, exploratory factor analysis(EFA) and reliability analysis for items evaluation, (7)confirmatory factor analysis(CFA) and correlation analysis for scale validation, (8)CFA, correlation analysis and structural equation model(SEM) test for predictive validity used second data collected(n=471). The current study conceptualized the service quality in the context E-SSMSQ by incorporating interaction, efficiency, order processing, information, security, and design. The authors also developed 20 items E-SSMSQ. The results of SEM support the psychometric property of the scale. First, interaction, efficiency and order processing of E-SSMSQ had significantly influence on internet shopping mall satisfaction. Interaction, efficiency, security, and design of E-SSMSQ had significantly influence on internet shopping mall intention of recommendation.

Originated from the reason that Hanoi University of Industry (HaUI)’s current social media network is still limited, specifically HaUI's Fanpage has not yet been green-checked, thereby leading to weak brand attachment have little impact on university admissions. From collecting data from information sources such as newspapers, social networking sites, the author has inherited previous studies to propose a research model and conduct quantitative research analysis. Through designing a survey questionnaire and randomly sending it to individuals who are studying and working at HaUI, specifically lecturers, staff and especially the university students. The study obtained 338 valid responses that were coded and cleaned using SPSS and AMOS software. After the cleaning and coding step, reliability testing, exploratory factor analysis, confirmatory factor analysis and structural equation modelling were conducted. The research has made a significant theoretical contribution in terms of the important mediation role of brand awareness, perceived quality and university reputation in the relationship between social media communication and brand attachment. From there, it also provided the practical contribution to improve the association of the brand with students, to perfectionate the social networking sites,to share positive things, interesting, attractive and relevant lessons.

Objective To explore the application of the Structure Equation Model on validity assessment of the evaluation indicator system,we studied Medical Capital Development Fund projects in 2007 to evaluate their construct validity.Methods Part of the evaluation results (1200 items) were divided into two parts randomly.PART1 was used for Exploratory Factor Analysis (EFA) to explore the Indicator System' structure,and formed model F1.Confirmatory Factor Analysis (CFA) was used to assess the construct validity of model F1.With considerations of Modification Index(MI) and reality,F1 was modified into F3.At last,we take PART2 as the sample to confirm F3.Result The results of model F3 fit indices showed a better fit.All the path coefficients,estimated load factors and other parameters were statistically significant.Conclusion Structural Equation Model is professional,reliable and satisfactory for the evaluation of indicator system's contract validity. Key words: Structural equation model; Indicator system; Exploratory factor analysi; Confirmatory factor analysis

The purpose of the present study was to provide a causal model of digital leadership factors in the formation of an innovative organizational culture in the universities of Mazandaran Province. The research method was applied in terms of purpose and descriptive–survey in nature. The statistical population included all employees of Islamic Azad University branches in the cities of Sari, Babol, Tonekabon, Chalous, Neka, and Behshahr in Mazandaran Province (1,030 individuals). The sampling method was proportional cluster random sampling based on university units, and the sample size was determined to be 280 individuals using Cochran’s formula. A researcher-made questionnaire was used to collect data for the two variables of digital leadership and innovative organizational culture. The face, content, and construct validity of the instrument were examined and confirmed by academic supervisors, advisors, and subject-matter experts. In descriptive statistics, the mean, standard deviation, frequency distribution tables, and charts were presented for each variable, and this process was performed using SPSS software. In inferential statistics, the Kolmogorov–Smirnov test was used to examine the normality of data distribution, and to address the research questions, single-sample and independent t-tests, correlation coefficients, exploratory factor analysis, and structural equation modeling (including exploratory and confirmatory factor analysis) were employed. In the inferential section, the research hypotheses were tested using SPSS as well as AMOS. The results obtained from AMOS software were interpreted using the structural equation modeling approach. Path analysis results indicated that digital leadership has a positive, direct, and significant effect on innovative organizational culture.

Safety is a major concern in the oil and gas industry due to accidents with the potential for catastrophic consequences. One of these was the Piper Alpha drilling platform disaster in 1988, which resulted in the loss of the Piper Alpha platform and the subsequently 167 lives; the worst disaster in the oil and gas industry. To foster a proactive approach in the prevention of workplace injuries, organisations have turned towards key predictors of safety, such as leadership. However, simply practising leadership behaviours is not enough to improve safety, especially in safety-critical organisations. An inability to move beyond the formal control inherent in traditional bureaucratic mindsets limits the applicability of mainstream leadership theories for safety-critical organisations. To address this challenge, this research study adopts a different paradigm for leadership, one which frames leadership as a complex interactive dynamic from which adaptive outcomes emerge as complexity science. Hence, the aim of this research study was to investigate the direct relationship between leadership behaviours and safety outcomes, and the mediating effect of complexity science principles. To accomplish this, a conceptual model was developed using theoretical foundation built from the literature review. The model comprises three main components: 1) leadership behaviours, 2) five complexity science principles (connectivity, interdependence, feedback, exploration-of-the-space-of-possibilities and co-evolution) and 3) three safety outcomes (safety participation, safety compliance and safety climate). These components were linked by the proposed hypotheses that were established based on assumed theoretical relationships. To assess and validate the conceptual model and test the hypotheses, a series of quantitative approaches were employed. A multivariate statistical approach was utilised for data collection through a questionnaire survey; 173 project managers participated in the survey. These individuals are responsible for emergency commands, as well as the day-to-day management of safety. Principal component analysis/Exploratory factor analysis was performed to identify the factor structures representing each underlying construct. Confirmatory factor analysis was conducted to validate the results obtained from the exploratory factor analysis, followed by multiple regression analysis. Next, structural equation modelling was applied to test the structural models for hypotheses testing. The regression analyses demonstrated that all three identified leadership behaviours — 1) empowering & engaging, 2) modelling & reinforcing, and 3) promoting & enabling — directly influenced the level of safety participation and safety compliance. Additionally, all five principles of complexity science mediated the relationship between empowering & engaging leadership behaviour, and safety participation and safety compliance. As for the hypothesised relationship between modelling & reinforcing leadership behaviour and safety outcomes, apart from the co-evolution principle, all other complexity science principles arbitrated the relationship with safety participation and safety compliance. Furthermore, the relationships between promoting & enabling leadership behaviour, and safety participation and safety compliance were mediated by all five principles of complexity science. Finally, structural equation modelling was used to refine and confirm the findings of the regression analysis, verifying both empowering & engaging, and promoting & enabling leadership behaviours have direct and indirect influences on safety participation and safety compliance levels as a result of all five complexity science principles. And established that modelling & reinforcing leadership behaviour has direct and indirect effects on safety participation and safety compliance levels under the influence of only four complexity science principles — namely, connectivity, interdependence, feedback and exploration-of-the-space-of-possibilities. On the basis of the research results, this study provides insight into the understanding of safety leadership by the empirical evidence that displayed the relationships between the three leadership behaviour constructs and their contribution to the effect of complexity science principles and safety outcomes within the oil and gas industry. From these results, the study provides a list of recommendations for research on the effect of leadership behaviours on complexity science principles and safety outcomes.

This study explored the relationships of senior high school EFL students' motivation, strategy use, and English achievement. The first two attempts of the study were to investigate how well the senior high school EFL students' motivation and strategy use can predict students' English achievement respectively. The third attempt was to explore the causal relationship among senior high school EFL students' motivation, strategy use, and English achievement.Totally 132 senior high EFL school boy students took part in the study. Two questionnaires-Motivation Questionnaire (Chen, 2008; Lai, 2008) and Strategy Inventory for Language Learning (SILL, version 7.0)-were used for data collecting.With SPSS for Windows Version 17.0, data analysis, including item analysis, exploratory factor analysis (EFA), reliability analysis, and validity analysis, was used. Furthermore, Structural equation modeling (SEM) was adopted through second-order confirmatory factor analysis (CFA) in LISREL 8.8 to confirm the causal relationships among senior high school EFL students' motivation, strategy use, and English achievement.The causal relationships between motivation and English achievement and between strategy use and English achievement were both proved. Motivation could account for 39% of the total variance toward English achievement while strategy use could account for 19% of the total variance toward English achievement. Intrinsic Motivation and Utilitarian Purpose took up the most variance toward English achievement, whereas Metacognitive Strategies was the only individual factor contributing to the total variance toward English achievement. The relationship among senior high school EFL students' motivation, strategy use, and English achievement was a full mediating model with a reciprocal relationship between strategy use and English achievement.

This study aimed to investigate the latent constructs in the Foreign Language Classroom Anxiety Scale using a research context of Japanese undergraduates who learn English as a foreign language. The study conducted both exploratory and confirmatory factor analysis against two different groups of Japanese undergraduate students. First, exploratory factor analysis was used to extract factors from 33 items of the scale in its application to 149 management major students. Subsequently, confirmatory factor analysis was conducted on the factors from the exploratory factor analysis. Data from 237 English language learners at two universities—155 undergraduates at a foreign study university and 82 at a general university—were applied to test a hypothetical model in relation to the extracted latent constructs. Results of the two factor analyses identified and confirmed two underlying components of the scale: (1) communication apprehension and (2) fear of failing. The model fit statistics illustrated that the two-factor paradigm appropriately fit the data from the second undergraduate group. Implications of the results are discussed.

10 Structural Equation Modeling

Aim: Lean is a set of operating philosophies and methods that help create maximum value for patients by reducing waste and waits. It emphasizes the consideration of the customer's needs, employee involvement, and continuous improvement. The aim of this study was of factors affecting lean management in public hospitals in Kohgiluyeh and Boyerahmad and Bushehr provinces. Materials and Methods: This research was descriptive correlation study. The questionnaire was used to collect the data. Factor analysis and multiple regression analysis were conducted to understand the relationship between these factors and lean implementation success. With using 60 questions questionnaire, the content validity of the method developed by the researchers and expert judgment and Cronbach's alpha and test–retest reliability of the method was investigated, and the opinions of 500 primary health-care practitioners were collected. Then, a two-stage exploratory and confirmatory factor analysis and structural equation modeling with the use of statistical software SPSS for Window 17.0 software (SPSS Inc., lllinois, USA) (Leland Stanford Junior University) and AMOS 20 carried out to review and modify the conceptual model. Results: Exploratory factor analysis identified five factors of human, technology, management, processes, and relational that explains 58.5% of the total variance. Confirmatory factor analysis also showed that among identified factors, technology factor with 0.953 coefficient has greatest impact and management factor with 0.615 coefficient has the lowest impact on the pattern of lean management in public hospitals to improve the quality of services. Conclusions: The factors affecting the deployment of lean management in public hospitals and appropriate strategy for using the lean management to improve the delivery of primary health care and reduce waste. The results represent guidelines for using effective implementation of lean management to increase efficiency and ability to compete in the global market offers.

PurposeOwing to religious and economic preferences in Muslim-dominated countries, middle-income customers are at the heart of banks’ strategic targeting. This study aims to investigate selected middle-income Islamic bank customers from Sylhet, one of Bangladesh’s top religious and cultural cities, to examine their perceptions of the Islamic banking services.Design/methodology/approachThis study forwards three determinants of overall satisfaction. These are perceived relative advantage (PRA), perceived risk management (PRM) and perceived customer engagement (PCE). The study has used structured questionnaire and collected complete data on 300 middle-income Islamic bank users. The data was analysed using exploratory factor analysis (EFA), confirmatory factor analysis (CFA) and structural equation modelling (SEM).FindingsWhile all the three selection factors significantly influence overall satisfaction, PCE has greater positive impact on overall customer satisfaction, followed by PRA and PRM. “Convenient location”, “competitive charges” and “return on deposit despite low earnings” are the top three instruments measuring “PCE”. Religion did not qualify as a standalone selection factor. The results are robust across tests conducted by using EFA, CFA and SEM.Practical implicationsGross purchasing power of middle-income class in Bangladesh grew from 7% to over 30% during the past decade, and the purchasing power of this class stood at US$100bn. Having a greater portion of this population as Muslims, banks can design products and marketing campaigns by using the three selection criteria that offer a combination of faith and non-faith-based variables.Originality/valueSimilar studies on the middle-income customer group have been rare, especially from the Islamic banking perspective. These findings offer a concise list of three factors for the bank managers to build their strategies. With respect to the Vision 2021, these findings carry greater socio-economic significance given the transition of Bangladesh to a middle-income country.

Objective: The aim of this study is to present a model for energy and environmental policy-making in GHRM for Mashhad Municipality. Methodology: This research is applied in terms of its purpose and descriptive-survey in terms of data collection methodology. The statistical population of this study consists of experts and managers of Mashhad Municipality, totaling 240 individuals. The sample size, calculated based on Cochran’s formula, is 143 participants. Data collection tools in the library method included note-taking, information databases, documents, and the internet. In the field method, qualitative questions were derived from review articles, and quantitative questions were collected using a questionnaire. To develop the questionnaire, various related articles were reviewed to explore green human resource management policy-making. After three stages of checklist compilation, an initial 34-item questionnaire was prepared. This questionnaire was then distributed among university professors. Using exploratory factor analysis, more significant factors were identified, and less important ones were eliminated from the questionnaire. The final questionnaire was prepared after responses were collected and was distributed among the study sample. Data analysis was conducted using structural equation modeling, exploratory factor analysis, and confirmatory factor analysis with AMOS software. Findings: The research findings, while validating the proposed model, revealed that the components of GHRM encompass individual, social, cultural, energy, environmental, organizational, and ecological dimensions. Conclusion: The results demonstrated the impact of energy, environmental, and ecological components of GHRM on the managerial components of the municipality, including the Deputy of Planning and Development, the Deputy of Finance and Support, the Deputy of Urban Services and Environment, the Deputy of Transportation and Traffic, the Cultural and Social Organization, the Deputy of Technical and Civil Affairs, and the Deputy of Urban Planning and Architecture.

The structure of mentors' behaviour in clinical nursing education: Confirmatory factor analysis

BackgroundGait impairment is a risk factor for falls in patients with Parkinson’s disease (PD). Gait can be conveniently assessed by electronic walkways, but there is need to select which spatiotemporal gait variables are useful for assessing gait in PD. Existing models for gait variables developed in healthy subjects and patients with PD show some methodological shortcomings in their validation through exploratory factor analysis (EFA), and were never confirmed by confirmatory factor analysis (CFA). The aims of this study were (1) to create a new model of gait for PD through EFA, (2) to analyze the factorial structure of our new model and compare it with existing models through CFA.ResultsFrom the 37 variables initially considered in 250 patients with PD, 10 did not show good-to-excellent reliability and were eliminated, while further 19 were eliminated after correlation matrix and Kaiser–Meyer–Olkin measure. The remaining eight variables underwent EFA and three factors emerged: pace/rhythm, variability, and asymmetry. Structural validity of our new model was then examined with CFA, using the structural equation modeling. After some modifications, suggested by the Modification Indices, we obtained a final model that showed an excellent fit. In contrast, when the structure of previous models of gait was analyzed, no model achieved convergence with our sample of patients.ConclusionsOur model for spatiotemporal gait variables of patients with PD is the first to be developed through an accurate EFA and confirmed by CFA. It contains eight gait variables divided into three factors and shows an excellent fit. Reasons for the non-convergence of other models could be their inclusion of highly inter-correlated or low-reliability variables or could be possibly due to the fact that they did not use more recent methods for determining the number of factors to extract.