No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
PLS-SEM: indeed a silver bullet
Figures
Figures - uploaded by Christian M. Ringle
Author content
All figure content in this area was uploaded by Christian M. Ringle
Content may be subject to copyright.
... A self-administered questionnaire was conducted from green hotels, data was collected from the hotel guests who stayed at the green hotels in HCM City, Vietnam. The first criteria for choosing the hotel guests, they must be 18 years and above, stayed at a green hotel at least one time, and agreed to participate in this study voluntarily, we used convenience sampling and snowballing sampling techniques to select the hotel guests (Mai et al., 2022;Yusof et al., 2017), because of convenience sampling where subjects are readily available and easy to recruit for the study, and it is in proximity of the researcher and a systematic sampling, it also provides an inexpensive way to reach a large sample, it makes the research more relevant and representative (Hair et al., 2011), whereas, snowball sampling is where a chain referral exists and a fast technique to recruit the target population. A researcher first selects a respondent to collect data then this respondent refers one or more respondents, and, in this chain, everyone refers one or more respondents until the requirements of the researcher are fulfilled (Hair et al., 2010). ...
... Regarding sample size, this research adopted a rule of thumb from Hair et al. (2013), the minimum sample size is 10 times the greatest total of structural paths directed in PLS-SEM at precise latent constructs (Hair et al., 2013), a conceptual model of this study consists of 10 constructs go with 51 indicators, so the minimum sample size was at least 510 the required samples (51 3 10 = 510 respondents were needed). To ensure the sample size is adequate for getting accurate and running this research model successfully, it's better to get more respondents to meet the generalization and reliability of data collection (Hair et al., 2011). ...
... This study employed the ''Partial Least Squares Structural Equation Modeling'' PLS-SEM to assess the structural equation models and test research hypotheses (Hair et al., 2013). Hair et al. (2011) pointed out that ''PLS-SEM is a regression-based approach to minimize the residual variances of the endogenous constructs'' (Merli et al., 2019, p. 172), the PLS-SEM was selected due to the exploratory and confirmatory nature of this research and can solve a complex research model by predicting the potential effective relationships among the latent variables (Hair et al., 2017), moreover, it can handle well the reflective factors and ''non-normal distributions relatively'' and the measures in this study were developed with a 5 Likert Scale, data are the ''non-normal data distributions'' (Hair et al., 2012). In addition, the PLS-SEM method performed well with the mediating variables analysis, which is used to explore the relationship among these constructs in this current research model, many studies also used this method (Hair et al., 2011). ...
The awareness of green innovation practices (GIP) is trending globally. It is still unclear how guests’ return intentions support GIP. Based on the theory of planned behavior (TPB) and innovation theory, this study explored the influence of GIP on guests’ return intention through the mediating role of green hotel image, guests’ positive mood, and guests’ satisfaction. Data was collected from 1,058 hotel guests and analyzed by utilizing PLS-SEM. The findings confirmed all the hypotheses, except water-saving didn’t affect guests’ positive mood, and energy-saving didn’t affect guests’ satisfaction, thus green hotel image, guest satisfaction, and guests’ positive mood mediated the relationships between GIP and guests’ return intentions. This study enriches GIP and customer behavioral intentions literature in the hospitality industry, hotel managers focus on GIP to improve guests’ satisfaction, and positive moods to enhance guests’ return intentions to the hotels, the results provide some suggestions for future research and managers of the hospitality sector with practical recommendations.
JEL codes: 03; M0
... The survey was conducted with 234 participants (23). (27). In confirmatory research contexts, Cronbach's alpha provides a more conservative estimate of construct reliability for rho_A and, while more conservative, is also relatively more robust (26). ...
... The model Figure 3 examines how financial knowledge, experience and skills indirectly contribute to financial well-being by influencing financial self-efficacy (23,24,27). This path analysis also examines model fit in terms of Rsquared, SRMR, Chi-squared, and NFI to assess the adequacy of capturing the relationship of these variables. ...
... With a path coefficient of 0.310, the result shows a medium positive relationship; therefore, financial skills contribute only slightly to building self-efficacy. The fact that it showed a positive effect at 0.332 shows that self-efficacy itself plays an important role in improving the aspect of financial well-being (24,27). The Rsquared for financial self-efficacy was 0.634; this is interpreted to mean that financial self-efficacy accounts for 63.4% of the variability in financial self-efficacy when accounting for financial awareness, financial experience, and financial skills. ...
This study examines the financial literacy of Generation X, focusing on dimensions such as financial awareness, experience, skills, self-efficacy, and overall financial well-being. The purpose is to understand the financial well-being Status by the X generation through financial literacy. A quantitative research design was employed using practical surveys distributed to a diverse 264 sample of Generation X individuals. Adopting convenience sampling, conducted survey in selected areas in Andhra Pradesh. The Data analysis was performed structural equation modelling, to identify relationships between financial literacy and wellbeing. The results show a significant positive relationship between financial literacy components and financial well-being and highlight that improved financial awareness and skills lead to increased financial self-efficacy. Additionally, the analysis shows that personal financial experiences significantly influence individuals' confidence in managing their finances. The discussion highlights the need for targeted financial education programs that address the unique challenges facing Generation X, particularly in an increasingly complex financial landscape. The implications of this research are far-reaching.
... The study used SmartPLS4 to measure the outer model and establish the validity and reliability of the obtained data. More specifically, convergent validity was established using Cronbach's alpha (α), composite reliability (CR), and Average Variance Extracted (AVE), with the values obtained considered acceptable, 109,110 at more than 0.70, 0.70 and 0.50, respectively. Individual study variables obtained the following Cronbach's alpha, CA, and AVE, respectively: COVID-19 anxiety was 0.714, 0.821, and 0.537, event-related fear was 0.909, 0.939 and 0.837, DCT tool intention to use variable obtained 0.917, 0.948, and 0.858, perceived ease of use was 0.854, 0.901, and 0.695, while perceived privacy was 0.914, 0.933, and 0.699. ...
... Fornell and Larcker (1981) were used to evaluate the measurement model and data validity 109,110 (refer to Tables 4 and 5). ...
... Following past studies, the structural model was exposed to a bootstrapping procedure with 5000 re-samples. 109,111,114 Last, the path coefficients were employed to test the direct, moderating, and mediating effects (See Table 6 and Figure 4). Table 6 tabulated results supported hypothesis 1, which posited a significant and positive association between the DCT tool's intention to be used by citizens and perceived usefulness (β = 0.177, t = 2.694, p < 0.01). ...
Objective
The emergence of more contagious SARS-CoV-2 variants, such as EG.5 (Eris), has heightened the urgency of assessing associated risks and managing the spread of infections. Digital Contact Tracing (DCT) tools have been widely adopted to mitigate these risks, although the factors driving their acceptance are complex and multifaceted. However, there is a significant lack of research on the application of DCT within Saudi Arabia, despite its proactive use of such technologies in public health strategies. This study investigates the key determinants of DCT adoption and acceptance by integrating the Technology Acceptance Model (TAM) with psychological, social, and regulatory factors related to the context of the study.
Methods
Using a quantitative, cross-sectional design, data were collected from Saudi participants through an online survey and analysed using Structural Equation Modeling (SEM) with SmartPLS4.
Results
The results supported all the hypotheses except for the relationship between social media awareness and DCT tool usage. The findings revealed that COVID-19-induced anxiety significantly influenced technology acceptance, with social influence playing a mediating role. This study introduces a novel, context-specific model contributing to the technology acceptance field by exploring how pandemic-related factors, such as anxiety and social influence, affect DCT tool adoption. It also addresses a critical gap in the previous literature by examining the mediating role of social impact in the association between privacy and event-related fear and the moderating effect of COVID-19 anxiety on social media awareness and DCT usage. The findings offer valuable insights for governmental interventions, health institutions, and legislators in managing pandemics globally and within the Kingdom of Saudi Arabia.
Conclusion
We introduce a novel, context-specific model for understanding how pandemic-related psychological and social factors influence DCT adoption in this study. Those results provide insight into how policymakers, health institutions, and legislators can use DCT tools to manage pandemics globally and in Saudi Arabia.
... Goodness of fit test allow researcher to determine whether the sample follows a normal distribution. Using three to four fit models is sufficient to show that this research model is acceptable, at least each of the absolute fit, incremental fit, and parsimonious fit are fulfilled (Hair et al., 2011). In addition, the model Goodness of Fit is evaluated by certain indicators as mentioned in Table 1. ...
... This model's CMIN/df score is 1,197 (<5.00), which is good; its RMSEA score is 0,024 (<0.08), which is also good; and its CFI and TLI scores are 0,991 and 0,988 (>0.90), suggesting excellent GOF. Overall, the ratings indicate that the Goodness of Fit model is satisfactory (Hair et al., 2011). According to Table 2, each indication of the research variable has a loading factor value greater than 0.5. ...
... Table 2 indicates that Cronbach's Alpha value. Cronbach's Alpha value between 0.70 and 0.90 are usually interpreted as meaning that the study is very satisfactory (Hair et al., 2011). Also, the total value of reliability is greater than 0.6. ...
The purpose of this study is to analyze the influence of entrepreneurial orientation including innovation, proactiveness and courage in taking risks in Pekanbaru City, Riau Province Indonesia. SMEs contributes largely to Indonesia's economy. However, these enterprises often struggle with limited resources leading to weaker performance. The research problem centers on identifying factors that can enhance the BP, mainly through Technology and CI. This study uses quantitative and descriptive research methods using SEM - AMOS 26. Data is collected using online survey. The research sample is a portion of the leaders or owners of SMEs in the songket business commodity using a non-probability delivery method, namely a purposive sampling. Sample of the study was 240 respondents. Conceptually, this study found interesting relationship between innovation, proactive, risk taking, technology, competitive intensity and business perfomance then called as entrepreneurial orientation. The empirical results reveal that technology and competitive intensity significantly mediate the relationship between EO and SME performance. Therefore, with new findings, the study extends the literature on serial mediation in the EO-performance of SMEs. This study has important implications for SMEs that are seeking to gain a competitive advantage. The findings offer an additional insight to managers on entrepreneurial orientation strategy to increase business performance. Keywords: Business Performance, Entrepreneurial Orientation, Innovation, SMEs
... Since the number of respondents in this study was somewhat low, the PLS-SEM will be used to analyse the data. One of the distinguishing characteristics of the PLS-SEM is that it can compensate for issues regarding sample size (Hair et al. 2011), which were experienced during this study. ...
... Firstly, it disregards data distributional assumptions and can address normality issues (Hair et al. 2019). Secondly, it can accommodate a relatively small sample size, which appears to be prevalent in studies in which prediction was the primary objective (Hair et al. 2011). PLS-SEM involves two stages of data analysis: measurement model and structural model. ...
... Convergent validity of research variables is examined with Average Variance Extracted (AVE) scores. Table 6 shows that the AVE scores of each variable of interest are above 0.5, which reflects acceptable convergent validity (Hair et al. 2011). Discriminant validity was evaluated through the Heterotrait-Monotrait Ratio (HTMT). ...
Market orientation and differentiation strategy are essential determinants of contemporary performance measurement practice. However, studies investigating the association between market orientation and differentiation strategy on the use of non-financial measures (NFMs) in an emerging economy setting are still limited. This study examines whether these factors affect NFM use and eventually firm performance. A survey method was used in which the questionnaires were distributed to Indonesian manufacturing firms. Analysis was undertaken using Partial Least Square (PLS) Structural Equation Modelling (SEM). The results from a survey of 41 Indonesian managers documented positive and significant associations between market orientation and differentiation strategy, market orientation and NFM use, differentiation strategy and NFM use, and NFM use and firm performance. Additional tests revealed significant mediating relations in which NFMs facilitate positive impacts of market orientation and differentiation strategy on firm performance. These findings demonstrate the effect of market orientation and differentiation strategy in influencing NFMs use and illuminate the integral role of NFMs in bridging positive associations involving market orientation, differentiation strategy, and firm performance. This study contributes to the contingency-based management accounting literature in an emerging economy context by providing empirical evidence for the association between market orientation, differentiation strategy, NFMs, and firm performance.
... We used partial least square-structural equation modeling (PLS-SEM version 3) as the conceptual framework proposed above included different measures (Henseler et al., 2016), as also backed by the earlier research (Chin, 2010;Hair et al., 2011). There are two assessments that have been conducted in the study such as measurement model and structural modelling assessment (Hair et al., 2011;Chin, 2010); the details of both are provided below: ...
... We used partial least square-structural equation modeling (PLS-SEM version 3) as the conceptual framework proposed above included different measures (Henseler et al., 2016), as also backed by the earlier research (Chin, 2010;Hair et al., 2011). There are two assessments that have been conducted in the study such as measurement model and structural modelling assessment (Hair et al., 2011;Chin, 2010); the details of both are provided below: ...
... 50,000 resampling bootstrap method to check the level of signicance (Hair et al., 2011). Therefore, the results revealed the acceptability of the measurement model. ...
Drawing from the social learning and self-determination theory, we investigated the employee outcomes resulting from the perceived responsible behaviour of their leaders in the organisations through affective and normative commitment as a mediator. The proposed hypotheses were tested using structural equation modeling and followed two steps. The researchers administered the survey to collect data targeting 370 Indian middle-level managers working full-time. The study revealed that perceived responsible leadership considerably influences employee satisfaction and productivity. Furthermore, along with the direct significant relationship among perceived responsible leadership, employee satisfaction, and productivity, the results also indicated the presence of an indirect effect. This research guides new-age leaders on inducing employee productivity and satisfaction by leading responsibly and enhancing their affective and normative commitment. This study uniquely contributes to responsible leadership literature by linking it with self-determination theory. This study uniquely extends the limited understanding of responsible leadership and its relationship with employee satisfaction and productivity.
... In order for standardised loading to be considered significant in a two-tailed test at the 5% rate, it must have a value of at least 0.708 and an associated t-statistic above ±1.96 (Hair, Ringle, & Sarstedt, 2011). The T-statistics in PLS-SEM were derived through the implementation of a bootstrap approach as described by Hair, Sarstedt, et al. (2012). ...
... An AVE is considered valid if the score is equal to or greater than 0.5 (50%). In order to assess the validity of convergence, it is necessary to consider the principle that variable gauges should exert a significant influence (Hair, Ringle, & Sarstedt, 2011). The convergence of each variable with a reflective indicator is assessed by evaluating the validity using the extracted mean variable (AVE). ...
... Thus, it can be explained that the root of AVE has a higher value than the relationship between the variables contained underneath. In this context, the value of the root of the square mean in each variable is higher than the value of the relationship between the variable and the other variables to be tested, so it can be said that the form has good discriminatory validity (Hair et al., 2011). Therefore, the results of the discrimination validity test conducted in this study using the Heterotrait-Monotrait Ratio technique can be found in the following table 4. The opinion of experts states that the cross-loading method and the Fornell-Larcker criterion are less sensitive in evaluating the validity of discrimination. ...
The purpose of this research is to evaluate self-efficacy, social support, and coping stress in relation to academic resilience of students in the Faculty of Education (FKIP) at Jambi University. This study utilizes a quantitative method and employs a questionnaire as the instrument to collect data from students in the Faculty of Education at Jambi University. The Structural Equation Modeling Partial Least Squares (SEM PLS) method is used to analyze and evaluate the causal relationships between independent and dependent variables. The research sample consists of 218 respondents who are students in the Faculty of Education at Jambi University. The four variables examined in this study are self-efficacy, social support, coping stress, and academic resilience of students. The p-values obtained are as follows: H1, the influence of self-efficacy on academic resilience of students, has a value of 0.001. Based on this value, the first hypothesis is supported or confirmed. For H2, the influence of social support on academic resilience of students has a value of 0.000. Therefore, the second hypothesis is supported or confirmed. Finally, for H3, the influence of coping stress on academic resilience has a value of 0.000. Thus, the third hypothesis is supported or confirmed. Therefore, this research concludes that all variables significantly influence the academic resilience of students in the Faculty of Education at Jambi University.
... The composite reliability values, which depict the degree to which the construct indicators indicate the latent construct, exceeded the recommended value of 0.7 while average variance extracted, which reflects the overall amount of variance in the indicators accounted for by the latent construct, exceeded the recommended value of 0.5 (Hair et al., 2011). Also, the Cronbach alpha internal consistency reliability values are also all above the recommended 0.7 (Chin et al, 2018). ...
... To assess the structural model, Hair et al. (2011) suggested looking at the R 2 , beta, and corresponding tvalues via bootstrapping procedure with a resample of 5000. The resample of bootstrapping procedure was done using 5000. ...
... The bootstrapping procedure was done in order to have p-values and t-statistics that can be used to test the hypotheses of the study in order to reject the null hypotheses of the study or otherwise. Hair et al. (2011) also suggested that, in addition to these basic measures, researchers should also report the predictive relevance (Q 2 ). Figure 2 showed the structural model results, the loadings and the R 2 values for human resource practices and employee turnover intention. The model below shows the calculated relationships and path coefficients. ...
This study assessed the effect of human resource practices on the employee turnover intention in commercial banks in North Central region of Nigeria. The study was motivated by the problem of high employee turnover in commercial banks in North Central region of Nigeria. The study was restricted to human resource practices components of Talent management, Performance management, Reward management and Placement in commercial banks as the independent variables of the study, while employee turnover intention in the commercial banks was the dependent variable. The study adopted a survey research design using only primary data for its analysis. The data was derived using a self-administered structured five-point Likert scale questionnaire as the research instrument for the study. The population of the study was all employees of commercial banks in North Central region of Nigeria which was undeterminable so the sample size of 463 respondents was determined using the Cochran (1971) sampling formula and 20% added to account for attrition. Partial Least Square Structural Equation Modelling (PLS-SEM) analysis was used as the technique for data analysis in the study. The major findings of the study include a negative insignificant effect of Talent management on employee turnover intention, a positive and significant effect of Performance management on employee turnover intention, a positive and significant effect of Reward management on employee turnover intention, and a positive and significant effect of Placement on employee turnover intention. The study recommended that talent management strategies in commercial banks in the North Central region of Nigeria should be adjusted while performance management, reward management and placement practices should be upheld.
... If a construct loaded blew this criterion, researchers must drop the items that were less than 0.7. To achieve the value of AVE and CR as per the criterion suggested (Hair et al., 2011), this study dropped items from the students' sustainable development (SSD1), two items from teaching pedagogies (TP1 and TP4), as well as one item from cross-cultural communications (CCC4). The delectation of the items was conducted systematically by deleting them individually, starting from the smaller value (Hair et al., 2016). ...
... Therefore, items CCC4, SSD1, TP1, and ETP4 were retained despite low loading. As per the recommendation, the study's items loading less than 0.7 can be retained if the AVE is 0.5 or above (Hair et al., 2011;Jr, Matthews, & Matthews, 2017;Sarstedt et al., 2016). The discriminant validity is good, as shown in Table 3, because each latent construct's AVE is more significant than its highest squared correlation with any other latent construct in the model. ...
... In this study, PLS-SEM is used to support the framework due to its ability to handle complex relationships and perform predictive analysis. With multiple constructs and intricate relationships involved, PLS-SEM's capability to manage and analyze these complexities makes it an ideal choice (Hair et al., 2011). This approach enables the researcher to examine how app permission concerns, privacy awareness, privacy experience, and self-efficacy influence privacy concerns, which serve as crucial mediators in the framework. ...
... To address this limitation, the study also used a full collinearity test with Variance Inflation Factor (VIF) values, as proposed by Kock (2015), to further assess common method bias. A VIF value of 5 or higher suggests high multicollinearity, indicating potential redundancy among predictors (Hair et al., 2011). This study showed that the value for VIF is less than the value of 5, indicating the absence of multicollinearity as shown in Table 1. ...
Apps for mobile devices have become crucial in daily life. Every day, millions of people rely on smartphone apps to perform a variety of crucial tasks. Mobile app shops have seen an expansion in the number of apps due to rising consumer demand. On the other hand, as people's concerns about online privacy have grown, privacy issues pertaining to internet use have become more important in recent years. However, this study found that building trust might help allay consumers' worries about privacy when it comes to using m-commerce apps in Malaysia. Consequently, the purpose of this study is to empirically investigate customers' trust by comprehending privacy concerns related to their use of m-commerce apps in Malaysia. The APCO model and Social Cognitive Theory (SCT) are further explored in this study. Data were gathered through an online survey conducted on Malaysian users of mobile applications. Only 292 of the 350 respondents' useful responses were examined using SPSS and SmartPLS statistical tools. The results demonstrated and validated (APCO) and (SCT) emphasis on people examining the risks and benefit when deciding whether to disclose personal information. Practitioners would apply the empirical findings to study and comprehend consumer preferences in light of these results. JEL classification: M3
... The factor loadings ranged between 0.72 and 0.80 for OL, 0.61 and 0.84 for the LC construct, 0.78 and 0.83 for SE and 0.69 and 0.79 for PS. As factor loadings above 0.40 are generally considered acceptable (Hair et al., 2011), all observed values fall within an acceptable range, indicating sufficient indicator reliability. Table 3 also presents the reliability and validity statistics for the constructs. ...
... The VAF value is computed by dividing the indirect effect by the total effect. According to Hair et al. (2011), if the resulting value exceeds 20%, it indicates the presence of partial mediation. Based on the values obtained in this study (47% for SE mediation and 27% for LC mediation), all proposed hypotheses were supported, confirming both hypothesized direct and mediating relationships. ...
Purpose:
This study aims to investigate the influence of organisational leadership (OL) on pay satisfaction (PS), examining the mediating roles of self-esteem (SE) and locus of control (LC) within the chemical industry, where safety and leadership dynamics are critically important.
Design/methodology/approach:
Structural equation modelling was used to test the proposed conceptual model. Data were collected through a survey administered to middle and senior managers from 86 chemical companies in Istanbul, Türkiye, yielding 741 responses. After addressing validity concerns, 709 responses were analysed using SmartPLS 4.
Findings:
The analysis demonstrates that OL has a significant and positive effect on SE and LC, both of which, in turn, enhance PS. Furthermore, leadership directly impacts PS, emphasising its multifaceted role in fostering positive employee outcomes.
Research limitations/implications:
The study is limited to the chemical industry in Istanbul, which may affect the generalisability of the findings. Future research could examine these dynamics across various industries and geographical regions to validate and extend the results.
Practical implications:
The results underscore the importance of cultivating strong leadership practices to enhance employees’ SE and LC, thereby improving PS. Organisations may benefit from leadership development programmes that target these psychological constructs.
Social implications:
The findings contribute to the literature on leadership and PS by elucidating the mediating roles of SE and LC. The study supports the view that effective OL positively shapes individual self-perception and job satisfaction outcomes.
Originality/value:
This study uniquely explores the interrelationship between leadership, SE, LC and PS in a high-risk industry. It offers empirical evidence of the pivotal role psychological mediators play in the leadership–employee satisfaction nexus.
... In this study, the Cronbach's alpha coefficient was 0.817. that the VIF varies from 1.01 to 1.28 and less than 5 (Hair et al., 2011), which makes the multi-collinearity a negligible problem. So it is suitable for further analysis. ...
... This study performed variance inflation factor (VIF) test to detect the degree of multi-collinearity. The results showed that the Variance inflation factor (VIF) values are from 1.01 to 2.57, which all below 5 (Hair et al., 2011), indicating that multi-collinearity is not a serious problem in this data set, which is suitable for further analysis. ...
Illegitimate tasks are prevalent stressors in the workplace. However, no consensus has yet been reached regarding how illegitimate tasks impact creative behavior, even though illegitimate tasks have attracted much attention from researchers in recent years. To address this research gap, both studies explored the effect of illegitimate tasks on creative behavior of knowledge workers. Study 1 used a daily dairy study involving 104 knowledge workers, while Study 2 conducted a survey at two time points involving 574 knowledge workers. The results found that the relational energy knowledge workers experience during interactions with their family members moderated the indirect negative effect of illegitimate tasks on creative behavior through ego depletion, such that the indirect negative effect was weaker when the relational energy level was higher. These findings establish a new theoretical framework to enhance our understanding of the effect of illegitimate tasks on creative behavior through the lens of psychological energy, based on ego depletion theory and interaction ritual theory. Practically, these findings provide strategies for organizations to mitigate the negative effects of illegitimate tasks on knowledge workers’ creative behavior by alleviating ego depletion and fostering relational energy.
... Educational leaders, including headmasters and their assistants, play a crucial role in determining the adoption and integration of new technologies within schools (Lee, 2020). Their decisions are influenced by various factors such as perceived benefits, ease of use, organizational support, social influences, perceived risks, and trust in the technology (Hair et al., 2011;Hwang & Tu, 2021;McKnight et al., 2002;Venkatesh et al., 2003;Zhang et al., 2022). Understanding these factors and their interactions is essential for fostering successful AI adoption initiatives in educational settings. ...
... To start with, Table 7 shows that all the values of VIF of the exogenous variables in the model were less than 5 for both CI and TR which is deemed suitable for assessing the model and multicollinearity was not a concern in the model (Hair et al., 2011). We used the inner VIF values because all the exogenous variables are reflective, not formative. ...
The adoption of artificial intelligence (AI) in educational administration is gaining momentum, yet understanding the factors influencing its acceptance remains critical. This study examines the adoption of Generative AI, specifically Gemini, by school headmasters, assistants, and administrative staff in Oman, with a focus on the mediating role of perceived trust. Grounded in the Unified Theory of Acceptance and Use of Technology (UTAUT) and trust theories, the research hypothesizes that performance expectancy, effort expectancy, social influence, and facilitating conditions influence continuance intention through perceived trust. Using a sample of 293 respondents from government and private schools, the study applies Partial Least Squares Structural Equation Modeling (PLS-SEM) to analyze the relationships among these constructs. The findings underscore the significant role of perceived trust as both a direct determinant of continuance intention and a mediator between other UTAUT constructs and continuance intention. The results indicate that performance expectancy, effort expectancy, facilitating conditions, and perceived trust positively impact continuance intention, while social influence does not exhibit a significant effect. Additionally, perceived trust mediates the relationship between effort expectancy, social influence, and facilitating conditions with continuance intention, but not between performance expectancy and continuance intention. Findings reveal that Gemini enhances decision-making accuracy by 37% and improves administrative efficiency by 42%, reinforcing its value in school administration. This study advances the theoretical understanding of AI adoption in educational settings and provides practical insights for policymakers, educators, and AI developers to enhance AI acceptance and implementation in school management.
... Therefore, the structural equation modeling (SEM) approach was chosen to accomplish the outcomes. SEM can be performed in two ways: covariancebased SEM (CB-SEM) and partial least squares SEM (PLS-SEM) (Hair et al., 2011). We employed the PLS-SEM technique, which can manage intricate models and attain high statistical power even with a small sample (Hair et al., 2011). ...
... SEM can be performed in two ways: covariancebased SEM (CB-SEM) and partial least squares SEM (PLS-SEM) (Hair et al., 2011). We employed the PLS-SEM technique, which can manage intricate models and attain high statistical power even with a small sample (Hair et al., 2011). Furthermore, scholars have argued that PLS-SEM is suitable for exploratory research, while CB-SEM is appropriate for confirmatory research (Ong & Puteh, 2017). ...
Government and public sector organizations focus on inclusiveness, transparency, security, and effectiveness. However, amid the ongoing deregulation and competition with private sectors, there are compulsions to leverage digital technologies for improving economic performance and customer satisfaction. In the above context, little is known about the role played by organizational capabilities in technology-led transformation of government. We employ SEM technique to validate our conceptual model that investigates the role of organizational capabilities on the degree of digitalization in the government organization and data for the same was collected from 196 government officials with relevant experience. The study found that effective digital strategy formulation increases employee digital capabilities and positively impacts digitalization in government. Vendor management capability is observed to mediate the relationship between digital strategy and digitalization in government while employee digital capability has an indirect impact through vendor management. Cultural and organizational barriers do not dampen the relationship between vendor management and digitalization in government. Our results integrate the dynamic capability framework with developments in digital transformation and technology sourcing literature.
... For data analysis, Smart PLS 4.0 was employed, utilizing the Partial Least Squares (PLS-SEM) modeling technique to test the research hypothesis. PLS-SEM is widely utilized across various research domains, and allowing researchers to explore complex conceptual models with multiple structures and variables (Hair et al. 2011(Hair et al. , 2019. With the sample size of 320 participants, the use of PLS in this study was appropriate. ...
... All CR values of this study surpass 0.7, and the factor loadings are greater than 0.7. Furthermore, the results of the Variance Inflation Factor (VIF) analysis indicate no issues with multicollinearity (Hair et al. 2011). Therefore, based on the findings presented in Table 2, the structure of the study is acceptable. ...
This study aims to explore whether tourists perceive virtual reality (VR) technology as a valuable means of exploring tourist destinations without physically traveling, particularly through the use of museum VR panoramic technology. Using a conceptual model derived from the updated IS success model and expectancy theory, the study examines the impacts of technology quality and environmental attitudes on the intention to reuse VR technology. It investigates the relationship between tourists’ perceived value of using VR panoramic technology to virtually visit the Dunhuang Mogao Grottoes in China and their intention to continue using VR for tourism, thereby shedding light on the motivational processes involved in VR utilization. The model was empirically tested in a field experiment involving 320 participants, analyzed using Smart PLS.
The findings indicate that, from a technology quality perspective, while visual quality enhance perceived immersion and, consequently perceived value, information quality does not significantly impact perceived value, nor does system quality improve perceived immersion. Conversely, from an environmental attitude perspective, efforts to mitigate the environmental impact of tourism significantly influences perceived value, which positively affects sustainability, low-effort pro-environmental behaviors, and willingness to sacrifice. In turn these pro-environmental behaviors and willingness to sacrifice positively impact sustainability, thereby increasing the intention to reuse VR technology. This study highlights the motivational mechanisms linking technological quality and environmental attitudes to intentions to reuse VR technology. It also affirms the potential of VR as a tool to mitigate the adverse effects of physical tourism and promote environmental sustainability.
... Before data collection, a power analysis was conducted using G*Power 3.1.9.6, indicating that a minimum sample size of N = 89 would be required to achieve 80% power for detecting a medium effect size (f² = 0.15) at a significance level of α = 0.05. The 10-times rule proposed by Hair et al. [24] was also applied to determine the appropriate sample size for the study. However, the study included a total sample of two hundred sixty-nine surpassing the recommended samples based on the power analysis and 10-tems rule. ...
... According to Henseler et al. [36], any ratio below the 0.85 threshold indicates good discriminant validity. They require theoretical justification for their conceptual overlap, ensuring the distinctness of constructs is maintained [24], [39], [36]. All ratios are less than the 0.85 threshold, indicating significant discriminant validity between the constructs [37]. ...
Purpose of the study: This study aimed to examine university students’ attitudes and behavioral intentions toward the JESI Interactive Learning Module using the Technology Acceptance Model (TAM), focusing on perceived ease of use and perceived usefulness. Methodology: A structured 5-point Likert scale questionnaire adapted from Davis (1989) was distributed via Google Forms. A total of 269 university students were selected using stratified random sampling. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) through SmartPLS 4.0 and descriptive statistics via Jamovi software. Main Findings: The findings revealed that PU (β = 0.495, p < 0.000) has significant direct effects toward attitude, while PEOU (β = 0.117, p < 0.144) has no significant direct effects toward attitude. Additionally, attitude (β = 0.594, p < 0.00) has also been found to have a significant direct effect toward behavioral intention to use. Additionally, the structural model demonstrated a good-fit in all PLS-SEM indices. Novelty/Originality of this study: This study is the first to apply TAM to evaluate JESI, a context-specific ILM in Philippine higher education. It advances theoretical understanding of technology acceptance and offers practical insights for improving ILM design and adoption across similar digital platforms in higher education institutions.
... Pengujian R-square dilakukan untuk mengukur pengaruh variabel bebas terhadap variabel terikat. Nilai R-square 0,75, 0,50, dan 0,25 menunjukkan kekuatan model yang dikategorikan sebagai kuat, sedang, dan lemah (Hair et al., 2011). ...
Penelitian ini menganalisis dampak layanan PayLater dan Peer-to-Peer Lending terhadap perilaku manajemen keuangan masyarakat Kota Semarang, dengan risiko gagal bayar sebagai variabel mediasi. Penelitian menggunakan pendekatan kuantitatif dengan metode survei, melibatkan 100 responden berusia 19–34 tahun yang dipilih melalui purposive sampling. Data dikumpulkan menggunakan kuesioner dan dianalisis dengan metode Partial Least Squares Structural Equation Modeling (PLS-SEM). Hasil penelitian menunjukkan bahwa PayLater dan Peer-to-Peer Lending berpengaruh positif dan signifikan terhadap perilaku manajemen keuangan serta risiko gagal bayar, baik secara langsung maupun melalui variabel mediasi. Temuan ini menegaskan pentingnya literasi keuangan dan kesadaran risiko untuk mengoptimalkan pemanfaatan layanan fintech serta mengurangi risiko gagal bayar
... According to Hair et al. [52] this method allows for the simultaneous testing of two models: a structural (internal) model that encompasses latent variables and a measurement (external) model that includes latent variables and their relationships with the indicators or items linking them.. ...
This study aims to investigate the relationships between attachment, commitment, and loyalty among football fans, while also examining the moderating effect of interactivity in the commitment–loyalty link. The objective is to better understand how emotional connections and digital engagement influence long-term fan behavior. A conceptual model was developed based on an extensive literature review and a preliminary qualitative study. The proposed hypotheses were tested through a quantitative survey conducted with 428 football fans. Data were analyzed using the Partial Least Squares (PLS) method to evaluate the relationships between the variables. The results confirm that fan attachment significantly and positively influences commitment, which in turn fosters loyalty. Furthermore, the level of interactivity between fans and the sports team moderates the relationship between commitment and loyalty, reinforcing the strength of this connection. This research highlights the dual importance of emotional and interactive dimensions in cultivating fan loyalty. It emphasizes that fostering attachment and maintaining meaningful digital engagement are essential strategies for sports organizations aiming to build and sustain fan loyalty. Sports managers should prioritize the integration of social media and digital platforms into their communication strategies. Enhanced interactivity not only strengthens fan commitment but also plays a strategic role in loyalty development, offering a competitive advantage in the management of sports teams.
... Juni 2021. Target minimal jumlah responden dari pengumpulan data adalah dengan mengacu pada teori ten times SEM PLS, yaitu sepuluh kali dari jumlah variabel laten pada model[33]. Pada penelitian ini terdapat delapan variabel, sehingga jumlah minimal target responden pada penelitian ini adalah 80 responden. Berdasarkan data dari 100 responden tersebut profil demografi responden dapat dilihat pada Tabel 1.Tabel 1. Demografi Responden pembelian virtual item pada game Mobile Legends. ...
MOBA atau Multiplayer Online Battle Arena atau biasa disebut action real-time strategy (ARTS) merupakan bagian dari real-time strategy (RTS). Salah satu jenis game aksi Multiplayer Online Battle Arena (MOBA) pada perangkat seluler adalah Mobile Legend. Game tersebut dibuat dan dikembangkan oleh perusahaan pengembang game dari Shanghai, China yang bernama Moonton. Game ini telah memiliki jutaan pemain di dunia. Terbukti dari sebuah market aplikasi play store dengan jumlah unduhan pada bulan April 2021 mencapai lebih dari 100 juta. Dapat disimpulkan 100 juta lebih perangkat smartphone telah menginstal game ini sejak peluncuran global untuk platform android pada 11 Juli 2016. Di Indonesia sendiri pengguna aktif bulanan dari jumlahnya mencapai 50 juta lebih, kondisi tersebut merupakan pencapaian terbesar dibandingkan dengan negara-negara lain. Adanya perkembangan sedemikian cepatnya dalam industri game, khususnya Mobile Legends, maka perlu adanya strategi bersaing secara efektif yang berfokus pada pelanggan. Penelitian ini berusaha untuk mengetahui faktor pendorong pembelian skin pada game Mobile Legends. Penelitian ini mengadopsi Theory of Consumption Value (TCV) dan juga Stimulus Organism Response sebagai dasar pembangunan model konseptual. Berdasarkan 100 data yang valid, keseluruhan hipotesis diterima. Seluruh variabel memiliki hubungan positif dan juga signifikan.
... In this study, Structural Equation Modeling (SEM) was adopted to examine the structural relationships among nine constructs and the actual usage of the AR-based Zappar learning platform. Adhering to the two-step approach recommended by Hair [39], the study first assessed the measurement model to ensure validity and reliability and then evaluated the structural model to test the research hypotheses and determine the model's overall suitability. ...
This study investigates the acceptance and utilization of Augmented Reality technology among mechanical engineering students in higher education at the University of Malta, utilizing the Unified Theory of Acceptance and Use of Technology model and the Community of Inquiry framework. The research was conducted in three phases: developing lecture scenarios incorporating AR elements, delivering these scenarios, and analyzing the data using structural equation modelling with SPSS and AMOS. Findings reveal that Performance Expectancy, Effort Expectancy, Hedonic Motivation, and Cognitive Presence significantly influence Behavioral Intention, while Social Influence, Habit, and Price Value do not. Moreover, Facilitating Conditions and Behavioral Intention significantly influence Use Behavior. Most notably, Cognitive Presence from the COI framework emerges as a critical element, highlighting the significance of fostering learners’ cognitive engagement to promote AR technology adoption in blended learning environments.
... As depicted in Table 07, the majority of the factors sufficiently (greater than 0.3) correlate with work engagement, and correlations among independent variables are less than 0.7 (Osborne & Waters, 2002). Further, according to Table 10: Coefficient Results, VIF values for all the variables are less than 5, while the tolerance level is greater than 0.2, which indicates that there are no multicollinearity issues in the data set (Hair et al., 2011). According to the Durbin-Watson test, the value is within the range of 1 to 3. Therefore, there were no autocorrelation problems (Field, 2009). ...
Employee work engagement has gained considerable attention since engaged employees construct positive work-related outcomes. Knowledge of antecedents of employee work engagement is essential for devising intervention strategies. Hence, the main purpose is to discover antecedents that have significant effects on work engagement in teaching context. A quantitative strategy was adopted, with a structured questionnaire administered to the entire working population. Multiple linear regression analysis and engagement score were the statistical methods used with SPSS software version 21. According to the results, eight of the 14 antecedents evaluated had a substantial impact on teachers' work engagement. Passion for teaching shows the higher effect, while staff recognition has the lowest effect. Furthermore, only 18% of teachers are actively engaged, with 43% engaged and 39% actively disengaged. Contextual novelty, a high sample size, and testing a model with 14 antecedents provide significant originality to the study. Further, empirical evidence has been provided to fill the knowledge gap on antecedents, particularly in general educational environments in Southeast Asia. This study provides insights for both school-level administrators and national officials seeking to improve pedagogical efficacy. Furthermore, this work suggests areas for future research.
... La metodología utilizada para este estudio fue de mínimos cuadrados parciales a través de modelos estadísticos fundamentos en lo teórico, que permitieron la incorporación de variables latentes y no observables. Estos modelos fueron utilizados gracias a sus ventajas basadas en su facilitad de uso con tamaños muestrales reducidos, al minimizar la cantidad de varianza no aplicada y valorar la fiabilidad y validez de los modelos mediante diversos criterios (Hair, 2011). ...
Traditional teaching practices have been transformed, thanks to digitalization and the commitment to fulfill the Sustainable Development Goals. In the coming years, Higher Education Institutions have the challenge of becoming agents of change for the formation of global citizens, through a process of improving the quality of education and research, in addition to developing soft skills and intercultural competencies in students, through inclusive education. On this path, virtual collaboration spaces, such as the Collaborative Online International Learning (COIL) and the Mirror Classes programs, are excellent strategies that allow accessible, inclusive and quality education through technology, collegial and academic work of university teachers and students from different areas of knowledge, in which tourism stands out. It was considered appropriate to reflect on the benefits of inclusive collaborative spaces through COIL programs and mirror classes to achieve quality and global education. For this cross-sectional research, of a mixed nature, a convenience sample was taken of 12 teachers from the area of tourism at the Autonomous University of the State of Hidalgo, who have participated in COIL projects and mirror classes applying the method of partial squares. The results show that the COIL projects and mirror classes are collaborativ. The results show that COIL projects and mirror classes are collaborative spaces that allow the development of disciplinary and technological skills demanded in the market, besides being an excellent strategy for the internationalization of institutions through inclusive education in tourism; specifically, it is concluded that the main benefits in the use of collaborative spaces are the development of disciplinary skills, the formation of competencies in teamwork and the achievement of collaborative learning, as part of the benefits detected in the students.
... Uji reliabilitas dilakukan dengan perhitungan Cronbach Alpha, yang menunjukkan bahwa indikator yang digunakan untuk mengukur konsep dalam penelitian ini cukup reliable. Nilai correlated item-total correlation dapat diterima bila nilai Cronbach Alpha lebih besar atau sama dengan koefisien Cronbach Alpha 0.60 (Hair, 2011). ...
In an interview with the field supervisor and technical implementing officers of activities involved in the implementation of construction work in the Public Works and Spatial Planning Agency of Padang Pariaman Regency, the current condition of small-qualified construction service providers tends to have weaknesses in management, mastery of technology, capital and limited experts and skilled workers so that it affects product quality, punctuality of implementation and efficiency of human resource utilization, and capital. The purpose of the study was to identify factors that influence the performance of small-qualified construction service companies in Padang Pariaman Regency and their dominant factors. The research method used is a qualitative quantitative method by distributing questionnaires to respondents, where the non-probability sampling method (no-random sample) was used in taking respondent samples. The results of the questionnaire were processed using SPSS factor analysis. The results of the study found 5 factors that influenced the performance of small-qualified construction service companies in Padang Pariaman Regency, namely managerial/organizational factors, external factors, equipment factors, economic factors, and human resource factors. The dominant factors that influenced the performance of contractors in Padang Pariaman Regency were managerial and technical factors with a % of variance value of 14.404%.
... Ngoài ra, hiệu quả giải thích của mô hình đạt ngưỡng tốt với giá trị R-square đạt 59% cho biến TAW và 60,1% cho biến WNWB, cho thấy các biến độc lập giải thích tốt các biến phụ thuộc. Hơn nữa, các hệ số VIF đều dưới ngưỡng 3 (cao nhất là 2,572), đảm bảo không tồn tại vấn đề đa cộng tuyến [51]. Các hệ số tác động đều có ý nghĩa thống kê, trong đó CS ảnh hưởng dương đáng kể đến TAW (β = 0,365; p < 0,001), HS ảnh hưởng âm đến TAW (β = -0,464; p < 0,001), và TAW có tác động đến WNWB (β = 0,330; p < 0,001). ...
Nghiên cứu phân tích tác động của căng thẳng thử thách và cản trở đến cân bằng công việc - cuộc sống (WNWB) thông qua vai trò trung gian của sự phát triển trong công việc, dựa trên thuyết tự quyết và mô hình tích hợp về sự phát triển con người. Kết quả phân tích định lượng từ các nhân sự từ 18-55 tuổi tại các doanh nghiệp ở Việt Nam cho thấy, căng thẳng thử thách có tác động tích cực, thúc đẩy sự phát triển trong công việc và cải thiện WNWB. Ngược lại, căng thẳng cản trở gây ảnh hưởng tiêu cực, làm giảm sự phát triển và khả năng đạt được cân bằng này. Vai trò trung gian của sự phát triển trong công việc giúp giảm thiểu tác động tiêu cực của căng thẳng cản trở và tận dụng lợi ích từ căng thẳng thử thách. Nghiên cứu cung cấp hàm ý quản trị, khuyến nghị các tổ chức tạo môi trường làm việc tích cực, giảm thiểu yếu tố cản trở để nâng cao hiệu suất và sự gắn kết của nhân viên.
... show that the highest VIF value of all constructs is 4.37, which is below the recommended threshold value of 5 (i.e., VIF < 5; Hair et al., 2011). We conclude that multicollinearity is not a major concern for this study. ...
Chatbots have been pervasively applied in online retailing to communicate with customers. However, attracting and converting customers with chatbots remains a challenge, and little is known about whether and how chatbots’ communication traits influence customer purchase intention. In this study, we draw on the stereotype content model to identify warmth and competence as two distinct traits of chatbot communication. Then, we employ interpersonal attraction theory to pinpoint perceived attraction as the underlying mechanism, where customer-chatbot similarity of communication trait plays a contingent role in shaping perceived attraction. Through a mixed methods design, we found that customers perceive higher attraction toward chatbots with the communication trait of competence, facilitating customer purchase intention. When the similarity of dyadic communication traits exists, we also found that customers perceive higher attraction toward chatbots with warmth. Our findings contribute to the literature on chatbot anthropomorphism and customer behavior. The study also provides practical insights into chatbot design for online retailing.
... We employed PLS-SEM to validate the research model as PLS can also offer many advantages over the covariance-based method, such as overcoming constraints about measurement level, sample size, distributional properties (multivariate normality), model identification, factor indetermination, and model complexity (Hair et al. 2011). Using PLS is appropriate as our proposed model is characterized by a high level of complexity with a higher-order construct. ...
Amid the pervasive integration of AI technologies across societal and industrial domains, understanding users’ trust in these systems becomes increasingly crucial. This study addresses the growing need to understand users’ trust in Generative Artificial Intelligence (GenAI) and explores the societal implications of this type of trust. Based on the socio-technical systems theory, this work employs the FAT (Fairness, Accountability, Transparency) framework and humanness factors of AI, anthropomorphism, social presence, and emotions, as antecedents of users’ human-like trust, which is proposed to influence users’ attitudes, perceived performance, and behavioral intentions. Structural equation modeling analysis (N = 244) reveals that fairness significantly enhances trust, while accountability and transparency do not. Social presence and emotions positively impact trust, whereas anthropomorphism shows no significant effect. Furthermore, trust shapes users’ attitudes, perceived performance, and behavioral intentions toward GenAI systems. This study contributes to the AI adoption and user trust literature by illuminating the main antecedents of human-like trust and showing its impact on user acceptance from a social-technical perspective. Beyond the academic contribution, this research highlights the broader societal relevance of user trust in GenAI, particularly regarding public concerns over black box issues and humanness features of GenAI systems.
... According to Masisa and Mwakyusa (2021), the research model may be predicted with the use of the SmartPLS approach. PLS is better suited for exploratory research with tiny sample sizes (Hair et al., 2011). Santoso et al. (2023), stated that the SmartPLS technique is recognised as a prominent and effective statistical tool for analysing certain composite correlations between the study variables. ...
Purpose
This aspect has driven several studies to evaluate the performance of manufacturing organisations to offer further insights into this sector. Accordingly, this paper aims to examine the impact of innovative performance on production and market performances. This is followed by investigating the effect of production performance on market performance and the mediating role of production performance on the association of innovative performance with market performance in manufacturing organisations.
Design/methodology/approach
A set of questionnaires was provided to 384 managers in Palestinian manufacturing organisations through convenience sampling. This was followed by data analysis through structural equation modelling (SEM).
Findings
It was found that innovative performance directly and positively impacted production and market performances. Specifically, production performance positively impacted market performance, while production performance partially mediated the association of innovative performance with market performance. Moreover, the interrelationships between the dimensions of organisations’ quality were focused on.
Research limitations/implications
Only three primary areas in Palestine were investigated, namely, Ramallah, Alkhalel and Jenin. Therefore, it is suggested that future research works gain data from more areas in Palestine to improve the external validity of the research. Furthermore, generalisability should be addressed with caution due to the use of convenience sampling in this research. It is noteworthy that Palestine is an occupied nation. Researchers may also validate the findings of this study by investigating additional manufacturing sectors, including pharmaceutical and electronic businesses.
Practical implications
Notably, the major practical implication in this paper emphasises the importance of managers’ awareness of innovative and production performances as the success elements for improving consumer fulfilment, overall profits and market share as important elements of market performance.
Originality/value
Notably, this research is distinguished from past research works that primarily emphasised the investigation into the general association of innovation with performance. It has also contributed to the manufacturing performance literature by further validating the performance scales. The method selected in this study, which is SEM SMART PLS, may also offer additional insights into the existing performance models by examining the interrelationships between innovative performance and dimensions of organisational performance, including the production and market performances of the manufacturing sector in Palestine, which is a developing and occupied nation.
Link: https://www.emerald.com/insight/content/doi/10.1108/jiabr-09-2023-0295/full/html?utm_source=smc_email_onboarding&utm_medium=email&utm_campaign=apa_author_journals_access_2025-5-12
... Convergent validity is obtained by calculating the AVE (average variance extracted) value, which is the average value of the variations that can be explained by these indicators. Based on the loading value whose criteria are greater than 0.7, it is stated to show a strong correlation between the indicators (Hair, et al., 2011). Second, the criterion for discriminant validity is cross-loading, an indicator is declared good if it has a discriminant validity value greater than 0.5. ...
Brand value that is based on consumers (consumer-based brand equity) and is developed through brand identity that is by consumers' thinking characteristics is still very limited, even though consumers' ways of thinking are very diverse. This research aims to determine the influence of brand identity and brand identity that matches consumers' way of thinking (BICS fit) on CBBE, which is linked to the mediating variable (brand image). Using the explanatory research method, 11,000 Instagram followers of the Toko Kecil club became the population. The sample consisted of 386 people (slovin) using a simple random sampling technique. The results of this research show that brand identity has a positive effect on CBBE, brand identity has a positive effect on brand image, brand image has a positive effect on CBBE, brand identity mediated by brand image has a positive effect on CBBE, BICS fit has a positive effect on CBBE, BICS fit has a positive effect on brand image, brand image has a positive effect on CBBE, BICS fit which is mediated by brand image has a positive effect on CBBE. The results of this research can help clubs strategically overcome problems that arise and can provide a deeper understanding of the importance of brand identity, cognitive style, and brand image in achieving CBBE in the futsal club industry.
... After the assessment of reliability and validity in first step of PLS-SEM, the second step is consisted of PLS structural model to examine the relationship between variables to test the study hypotheses based on direct effect and indirect effect (Hair et al., 2011;Hair Jr et al., 2016;Streukens & Leroi-Werelds, 2016;Yusif et al., 2020). The PLS structural model is reported in Fig. 4 and results are reported in Table 4. ...
The objective of this research was to measure the structural relationships between intelligent algorithm recommendations, data collection, student-level engagement, feedback loop and healthy social mentality. The respondents of the current study were college students in China. In this method, primary data was collected from the respondents using a self-administered questionnaire and 1752 responses were considered to analyze the data. A partial least square–structural equation model (PLS-SEM) was used to measure the findings. The study found that data collection does not affect the healthy social mentality of the students. Furthermore, it was discovered that there were significant correlations between intelligent algorithm recommendations, data collection, student-level engagement and feedback loop. The study also found the significant impact of intelligent algorithm recommendations on data collection, feedback loop and healthy social mentality of the students. Besides, student engagement level is confirmed as a significant mediator between data collection, feedback loop and healthy social mentality of students. The research contributes a novel framework to the knowledge which addresses gaps in the previous studies. The discussion of intelligent algorithm recommendations for students’ healthy social mentality in this research is novel. This research highlights the importance of intelligent algorithm recommendations for improving the healthy social mentality of college students. It is useful to deal with data management related to the students, improving student engagement and addressing feedback loops that are critical for students’ healthy social mentality.
... Standardized Beta coefficients, which quantitatively range from 0.000 to 1.000, were used to interpret the path coefficients of the Partial Least Squares (PLS) structural model (Lowry & Gaskin, 2014) Hair et al. (2017 highlighted those values below 0 and 1 are typically regarded as non-significant. While non-significant or opposing paths do not support the earlier hypotheses, significant paths in the hypothesized direction offer empirical support for the proposed causal relationship (Hair et al., 2011). For direct associations, Smart PLS4 determined the significance of the route coefficients and associated t-values using a consistent PLS-SEM bootstrapping process. ...
The study sought to determine the effect of organisational support (OS) for energy-saving, water conservation, and waste management practices implementation on hotel performance (HP) in conservation areas in Uganda. The study used a correlational research design with quantitative methods about OS and HP. Krejcie and Morgan's 1970 sample size determination table was applied in selecting 265 participants from a population of 851 employees in 19-star-rated hotels from the study area. These participants were selected using multistage sampling consisting of stratified, proportional, and simple random sampling. Data was collected via self-administered questionnaires distributed with the help of trained research assistants. Construct validity was evaluated through factor analysis, using both exploratory factor analysis (EFA) and confirmatory factor analysis (CFA). Data was subjected to descriptive and factor analysis in SPSS 25 and partial least structural equation modelling (PLS-SEM) in SmartPLS4 for modelling and hypothesis testing. The results indicate that the OS accounts for 54.4% (R2 =0.538) of the variation in hotel performance. Specifically, the results show that OS (P<0.05), had a direct significant effect on hotel performance in conservation areas in Uganda. The blindfolding results confirm adequate predictive relevance, with the lowest Q² value at 0.538. The results show that all of the Q2 predicted statistics for the endogenous latent variable and the measurement variables of the endogenous construct are greater than 0. The study concluded that organizational support mechanisms for green environment practices implementation are essential, and have a significant effect on hotel performance in conservation areas in Uganda. The results of this study are useful to policymakers and industry practitioners by providing relevant insights in guiding decision-making to improve hotel performance. It also adds to the existing body of knowledge on the discussions relating to organizational support and hotel performance.
... PLS-SEM was used to analyze the collected data (Hair et al. 2011). There were no reliability and validity results for the constructs of the perceived presence of others, helping intention, and monetary donation because they were measured with a one-item scale. ...
... A computer programme called SPSS (version 25.0) and a comprehensive structural equation modelling (SEM) programme known as Analysis of Moment Structures (AMOS) (version 21.0) were utilised to conduct a quantitative analysis of the data. SEM was applied in this investigation as it is the most effective method when distinguishing between several constructs based on whether they are exogenous or endogenous, with each construct represented by multiple measurable variables (Hair et al., 2011). ...
This study evaluates the relationship between Emotional Intelligence (EI) and Teacher Effectiveness (TE) among faculty in Indian colleges using an empirical approach. Four dimensions of EI—Self-Emotional Appraisal (SEA), Others’ Emotional Appraisal (OEA), Regulation of Emotion (ROE), and Use of Emotion (UOE)—were assessed to determine their impact on TE. Data were collected from 600 college teachers using the Wong and Law Emotional Intelligence Scale (WLEIS), which comprised sixteen items. The findings reveal a significant relationship between EI and TE, with UOE demonstrating the most substantial impact. Employing Linear Structural Equation Modelling (SEM), the study confirmed that the measurement, structural, and overall models aligned well. However, the research has limitations, including its reliance on quantitative methods and self-report measures, which may introduce social desirability bias. Future studies should incorporate qualitative methods and explore the integration of EI into academic curricula. Practical implications suggest targeted interventions to enhance EI components, thereby improving TE cost-effectively. This research underscores the importance of culturally relevant EI strategies in enhancing teacher performance in Indian higher education, offering valuable insights for policymakers and educational stakeholders.
The purpose of this study is to determine the relationship and influence between religiosity, halal product awareness, consumer confidence, and purchase intention of Muslim consumers. The information used in this study comes from survey responses distributed to 250 Muslim consumers who have made purchases at Waroeng Steak and Shake Yogyakarta Special Region. Non-probability sampling with a purposive sampling approach is the sampling methodology used in this study. Purposive sampling is used in this study because it is necessary to meet specific criteria before selecting a sample in order to answer certain research questions in addition to providing representative values. Hypothesis testing used in this study uses Structural Equation Modeling (SEM) statistics using the PLS program with the aim of testing the correlation between variables that have been hypothesized in this study. The results of this study indicate that there is an effect of religiosity, halal product awareness, consumer confidence, and buying interest of Muslim consumers.
This research is research that examines the relationship between the attitude of beauty influencer Tasya Farasya and consumer purchase intention which is mediated by consumer attitudes towards Influencers. This research aims to identify the influence of influencer attitudes which include the dimensions of credibility, trustworthiness, expertise, liking, similarity, familiarity and attractiveness which are mediated by attitudes towards influencers in influencing consumer purchase intention. This research uses a quantitative approach using primary data in the form of a questionnaire as a research data collection tool. The data in this research was processed using SEM (Structural Equation Modeling) with the help of AMOS to test the research hypothesis. This research produces findings that attitudes towards influencers can mediate the positive and significant influence of beauty influencer Tasya Farasya's attitude on consumer purchase intention. The results of this research provide important insights for marketers and social media practitioners in understanding how attitudes towards influencers, especially in terms of credibility, trustworthiness, expertise, likeability, similarity, familiarity and attractiveness, can influence consumer purchasing interest.
Human consumption of snakes is listed as one of the main threats to their conservation status. Consumer behavior change interventions are identified as the most effective means to conserve species threatened by human consumption. However, knowing which behavioral drivers of consumption intention to focus on is necessary to guide change interventions effectively. This study determined the factors influencing behavioral intentions to consume the Vulnerable (VU) snake species Bitis gabonica in Ghana. Data were collected from 296 households in the Avatime traditional area in October and November 2024 with in-person interviews using a structured questionnaire. Analysis was done using the partial least square structural equation modeling (PLS-SEM) technique in SmartPLS 3.2.8. The findings revealed that the paths between attitude perceived behavioral control, and social norm towards consumption intention of Bitis gabonica were positive and significant. Attitude was the most important predictor of Bitis gabonica consumption followed by perceived behavioral control, and subjective norm. The study recommends behavior change campaigns that emphasize changes in attitude toward human consumption of Bitis gabonica . Persuasive messages focused on changing beliefs and emotions towards snakes should be the aim of attitudinal change efforts.
To clarify changes of discharge (Q) and sediment yield (SSY) during flood events provide critical insights for flood disaster prevention and control. However, our understanding of the long‐term variations and driving factors of Q‐SSY relationships during flood events remains limited. This study examined the variations in Q, SSY, and sediment rating curves (SSY = aQb) during maximum one, three, and five flood events (ranked by peak discharge) across 15 catchments in the China's Loess Plateau during 1956–2019. We used the partial least squares‐structural equation modeling (PLS‐SEM) to quantitatively decouple the effects of driving factors (precipitation, soil, vegetation, topography, and soil and water conservation measures (SWCMs)) on Q‐SSY relationships. There was a significant declining trend in both Q and SSY during flood events across catchments, but their contributions to annual SSY significantly increased by 41.48%, underscoring the critical role of floods in sediment transport. The Q‐SSY relationship during flood events became weakened over time, with coefficient a decreased and index b increased. The five driving factors explained 44%–49% of the changes in coefficient a and 36%–51% in index b. Significant direct effects of vegetation (path coefficient (β) = −0.921) and precipitation (β = 0.616) on coefficient a were observed (p < 0.05). Index b was principally dominated by SWCMs and vegetation, and the effects diminished with increase in number of flood events. These findings highlight the importance of vegetation cover and SWCMs in mitigating sediment transport, offering valuable insights for sediment management strategies in the Loess Plateau and similar regions.
Recent research has paid considerable attention to the role of university support in explaining student entrepreneurship, with several studies presenting empirical evidence of the moderating effects of individual traits on the relationship between university support and entrepreneurial intentions. However, the moderating effect of entrepreneurial capacity on this relationship has not been considered. This is particularly true in the Chinese context, where college students are reluctant to start businesses despite the substantial entrepreneurial support provided. Grounded in the theory of triadic reciprocal determinism, this study aimed to investigate the link between university support and entrepreneurial intention and examine the mediating role of students’ entrepreneurial capacity. Survey data were collected from 1,058 undergraduates in China’s Anhui Province and analyzed using structural equation modeling with partial least squares estimator. We found a positive but weak effect of university support on students’ entrepreneurial intentions, indicating that students are unlikely to obtain sufficient support directly from a wide range of university resources. However, university support significantly enhanced students’ entrepreneurial capacity, which, in turn, predicted students’ intention to create new enterprises. Our study also found that entrepreneurial capacity played an intermediary role between university support and students’ entrepreneurial intentions. These findings have several practical implications for policymakers and university administrators in terms of enhancing entrepreneurial support and students’ entrepreneurial intentions. This study contributes to the literature on student entrepreneurship in emerging economies.
ARTICLE INFO ABSTRACT Nowadays, service industry is facing a huge competition due to introduction of AI (Artificial Intelligence). Different organizations are working on the interface of AI in service recovery process and, consequently, measuring different customer behaviors. Customer on the basis of different service recovery strategies supported by AI system are generating very positive behaviors. Due to technological advancement organizations are not lagging behind it. The current manuscript measures the impact of service recovery strategy on customer behaviors when AI-powered customer relationship management (AI-CRM) technology mediates the relationship. All this model is measured in accordance with the technology of AI. All the hypotheses are accepted and shows positive results. Healthcare sector was used as population. Data of 320 customers were collected (patients / attendees using healthcare service at time of data collection). This later study presents implications for the service industries and policy makers keeping in context the AI as important tool. Few of AI constraints are also included in future study and limitations of the study.
This study aims to examine the relationship between perceived financial risk (PFR) and online purchase behaviour (OPB) via online purchase intention with the contingency role of financial technology (Fintech) availability. The data was collected from 380 respondents and was examined using SPSS and Warp PLS 6.0. Contrary to hypothesised relationship, research findings show that PFR is positively and significantly linked to online purchase behaviour via online purchase intentions. The results further assert that Fintech availability positively moderates the relationship between PFR and OPB irrespective of gains and losses associated with the changing market dynamics. Positive moderating effect of Fintech availability on PFR and OPB clearly indicates that perceived risk associated with online purchasing can be mitigated through Fintech. This research contributes to the body of knowledge by explaining the PFR and OPB relationship via online purchase intentions and furthermore, by advocating the role of Fintech availability as a boundary condition.
By drawing on protection motivation, the study explored consumers' motivations to engage in adaptive behaviour from offline to online shopping during the pandemic. This study aims to find the impact of protection motivation, online trust, and perceived ease of use on online shopping attitudes in the post-pandemic period. A quantitative research design was employed, and data were collected from online shoppers using an online survey. The total number of respondents was 373, including both males and females. Additionally, the study used a convenience sampling method. Data were analysed through confirmatory factor analysis and PLS SEM. The findings of the study state that threat appraisal, online trust, and perceived ease-of-use positively impact adaptive behaviour by increasing online shopping attitudes. In contrast, Coping Appraisal has no direct effect on adaptive behaviour. This study provides a blueprint for designing marketing activities and strategies and assists managers in making decisions effectively during health crises and challenging events. The managers can formulate contingency strategies and plan to overcome the situation. The pandemic has been examined as an accelerator to adopting online shopping. Managers might adapt to the digital transformation in the market to recover or even grow sales further after the pandemic.
Entrepreneurship is a vital economic engine, but Indonesia's entrepreneurial rate is lower than other ASEAN nations, prompting government intervention to encourage student entrepreneurship. Due to the uncertainty, resource constraints, and diverse abilities required to start and run a business, many students are hesitant to pursue entrepreneurship. This study examines how entrepreneurial education activity promotes business opportunity recognition, perceived behavioral control, and entrepreneurial attitudes, which impact entrepreneurial intention and action using the Theory of Planned action framework. This study also examines how perceived university and government assistance might bridge the gap between student entrepreneurship intention and behavior. Using judgmental sampling, data from 483 Indonesian student entrepreneurs were collected online and analyzed using PLS-SEM for hypothesis and moderation testing. The findings indicate that entrepreneurial education activity improves business opportunity identification, perceived behavioral control, and entrepreneurial attitudes. Entrepreneurial attitude enhances both entrepreneurial intention and behavior, whereas perceived behavioral control has a direct impact on entrepreneurial behavior. Recognizing business opportunities emerges as a strong motivation for entrepreneurial behaviour. Furthermore, perceived university support positively influences entrepreneurial behavior, whereas government support positively moderates the association between intention and behavior. These results highlight the significance of education and institutional support in developing student entrepreneurship.
The increasingly rigorous business competition in the higher education industry requires every private university to improve its competitiveness by utilising all available resources. This study aims to examine the determinants of competitive advantage by mediating the performance of A-accredited and excelled study programmes at private universities in LLDIKTI Region III. The factors studied include lecturer competence, organisational commitment, and application of information technology. The research method used is a survey to the object of this research, namely all Study Programs at Private Universities that have A and Excelled Accreditation under the LLDIKTI Region III Jakarta, with a total of 314 Study Programs and a sample size of 250. Data were analysed using multiple regression analysis and path analysis. The results showed that the performance of A-accredited and excelled study programmes mediated the relationship between the determinants of competitive advantage and competitive advantage itself. The managerial implication of this research is that private universities in LLDIKTI Region III can increase competitive advantage through improving the performance of A and excelled accredited study programmes and the determinants of competitive advantage that have been studied.
This research examines and analyzes the effect of the economic pillars of the sustainable development goals (SDGs) on the sustainability of millennial entrepreneurs mediated by competitiveness. The background of this research is the value of Total Early-stage Entrepreneurial Activity (TEA), which is only 8.1%, ranked 36th out of 49 countries studied. This study uses an explanatory survey method, with data collection techniques through questionnaires distributed to millennial entrepreneurs in West Java Province who take part in education and training at the Office of Cooperatives and Small Businesses, totaling 250 people. The data that has been collected is then analyzed using SEM-PLS to produce more accurate conclusions and explore the relationship between variables. The results showed that the economic pillars of sustainable development goals (SDGs) can influence the sustainability of millennial entrepreneurs mediated by competitiveness. This finding implies that it is necessary to increase competitiveness to support the economic pillars of the SDGs.
This research examines the significance of dynamic capabilities in digital
transformation and explores the mediating role of a well-defined approach to
change management in the context of digital projects in the Yemeni
telecommunications sector. A quantitative research approach is used to
investigate a population of 902 managers and team leaders working in the
telecommunications sector in Yemen. A questionnaire was developed and
administered to a random sample of 316 participants, and the data collected were
analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM)
via SmartPLS version 4. The findings reveal a statistically significant positive
impact of dynamic capabilities and change management on digital transformation
projects. Furthermore, the findings revealed the mediating role played by change
management in the relationship between dynamic capabilities and digital
transformation projects. The results of this research contribute to the body of
knowledge in the literature by substantiating a positive relationship between
organization’s dynamic capabilities, effective change management techniques,
and the successful implementation of digital transformation initiatives.
Furthermore, the results provide valuable insights into the theoretical framework
underlying this topic by integrating dynamic capabilities, change management,
and digital transformation. In addition, findings can be beneficial for leaders in
the sector to develop and maintain capabilities that sense, seize, and transform
new technologies to drive their business transformation. Finally, the proposed
approach to change management helps leaders overcome the resistance to change
associated with new processes or business models brought about by new
technologies.
This study investigates how Total Quality Management (TQM) fosters sustainability in Thailand’s five-star hotels by shaping Green Organizational Culture (GOC), influencing Employee Green Behaviour (EGB), and driving Organizational Green Performance (OGP). A survey of 385 hotel employees in Bangkok, analysed via Partial Least Squares Structural Equation Modelling (PLS-SEM), reveals that while TQM strongly cultivates a green culture—fully mediating its impact on OGP—green behaviours alone fail to enhance organizational performance, suggesting unintended trade-offs. These findings challenge conventional wisdom that sustainability efforts always translate into performance gains, highlighting the need for strategic alignment between environmental and business objectives. Practical recommendations include integrating TQM-driven sustainability with employee incentives and regulatory frameworks to maximize impact. Future research should explore external forces, such as policy interventions and market demand, to better position sustainability as a competitive advantage in hospitality. This study advances the discourse on sustainable management by linking quality practices to environmental and operational outcomes.
Institutional entrepreneurship and sustainable entrepreneurship have been proposed as panacea to environmental degradation and negative impact of climate change caused by unsustainable business practices of entrepreneurs. Thus, this study examined effects of institutional entrepreneurship on all three dimensions of sustainable entrepreneurship among owners of micro and small businesses in the south western Nigeria. Although 300 copies of questionnaire were administered to the respondents, the field work yielded 65% (188) response rate and the results showed institutional entrepreneurship significantly predicted sustainable entrepreneurship – environment and sustainable entrepreneurship – social. However, no significant relationship was found between institutional entrepreneurship and sustainable entrepreneurship – economic. It was recommended that policy makers across all levels of government put in place necessary interventions to encourage sustainable entrepreneurship that simultaneously focuses on people, planet and profit.
The aim of this research is to analyze the influence of school leadership and management, organizational communication, work environment, and teacher participation on student academic achievement. Effective leadership, efficient management and good communication in school organizations aim to create a work environment that is conducive to increasing teacher participation in the teaching and learning process. Optimal teacher involvement is considered to be an important factor in increasing student motivation and improving academic achievement. Data was collected using a questionnaire designed to measure teacher perceptions of school leadership, organizational communication, and the work environment, as well as related to student performance as measured by academic achievement. The research results show that school leadership, effective management, and good organizational communication have a significant influence on student achievement through increasing teacher involvement. Therefore, improving school leadership, good management and effective communication in schools is a strategic step to improve student performance. Keywords: leadership, school management, organizational communication, work environment, teacher involvement, student achievement
Due to the ramifications of the COVID-19 pandemic, several university students may find themselves unable to engage in conventional English language learning in a physical classroom setting. The imposition of online English instruction compromised the efficacy and outcomes of students' English learning. Therefore, there is a need for a diverse range of technology, media, and platforms to enhance their educational achievements. Using mobile devices and wireless networks to interact with other devices may improve the effectiveness of online English learning for students. To investigate university students' learning behaviors and attitudes, when using e-learning to study English, the current study aimed to assess curiosity, self-efficacy, equipment, experience, perceived ease of use, perceived utility, attitude towards using e-learning resources for English language acquisition, and the actual use of those technologies. This study used questionnaires sent to 4 universities, resulting in a total of 751 valid surveys. This research used Smart-PLS 4.0 to analyze the structural model and validate the hypotheses. The hypothesis testing findings revealed that attitude is the most influential factor in determining the adoption of e-learning for English language acquisition. Both results indicate that variables in the TAM (ease of use and usefulness) have a significant impact on e-learning use outcomes. Likewise, interest, self-efficacy, equipment, and experience factors are influencing e-learning use. In this regard, the research outcome provides rich theoretical understanding and immense practical explanatory power in language acquisition
The COVID-19 pandemic has significantly disrupted the global tourism industry, restricting access to verious destinations While several studies have explored tourist perceptions of virtual reality and related behavioral intentions, limited research has focused on Sardinian tourism. This study investigates how virtual tours influence attitudes toward exploring Sardinian historical sites and intentions to visit them physically. Drawing on an integrated theoretical framework combining the Stimulus–Organism–Response (SOR) model and Technology Acceptance Model (TAM), the study evaluates the utilitarian aspects of VR, specifically perceived ease of use and perceived usefulness. Using structural equation modeling (SEM) on data collected from 517 valid respondents, findings reveal that both constructs significantly shape users’ attitudes toward VR. In turn, these attitudes positively influence the desire to explore historical sites virtually and subsequently translate into intentions for in-person visits. Moreover, the perceived risk of COVID-19 moderates the relationship between attitudes toward VR and the intention to visit, highlighting its role in digital decision-making. This research contributes to a deeper understanding of VR’s role in post-pandemic tourism and offers practical implications for destination marketers and outline potential directions for future research.
Purpose: This paper demonstrates the analyses of the role of educational and family support for the development of personal skills and risk willingness, which are important for pursuing entrepreneurial ventures. Entrepreneurship is seen as a critical component of economic development and growth, particularly in developing countries. Design/Methodology: The data was collected from three universities ((SIMAD University, Somali National University and Mogadishu University) in Banadir region purposively selected based on their research publication, formation of entrepreneurial sites, entrepreneurial fields, and entrepreneurial faculties. The study randomly selected 306 students across eight faculties from total population of 350 using Slovin’s Formula, the study utilized multiple linear regressions as technique of data analysis. The study used structural models through PLS software. Findings: The results revealed that that educational and family support significantly and positively impacted entrepreneurial intentions. The role of mediating variables (personal skills and risk willingness) also improves entrepreneurial intentions among graduate students. Moreover, the model shows that the changes of independent variables explain 34% of the changes of dependent variable, while the remaining 62% of changes might explained by unidentified factors which are not incorporated in the model. Recommendations: Thus, it is recommended that the private financial institutions and public institutions work together to establish micro finance center for the position of inspiring entrepreneurship joint ventures or ventures in the country.
We reflect on the role of structural equation modeling SEM in marketing modeling and managerial decision making. We discuss some benefits provided by SEM and alert marketing modelers to several recent developments in SEM in three areas: measurement analysis, analysis of cross-sectional data, and analysis of longitudinal data. q
In this article, we provide guidance for substantive researchers on the use of structural equation modeling in practice for theory testing and development. We present a comprehensive, two-step modeling approach that employs a series of nested models and sequential chi-square difference tests. We discuss the comparative advantages of this approach over a one-step approach. Considerations in specification, assessment of fit, and respecification of measurement models using confirmatory factor analysis are reviewed. As background to the two-step approach, the distinction between exploratory and confirmatory analysis, the distinction between complementary approaches for theory testing versus predictive application, and some developments in estimation methods also are discussed.
Heywood cases represent the most common form of a series of related problems in confirmatory factor analysis and structural equation modeling. Other problems include factor loadings and factor correlations outside the usual range, large variances of parameter estimates, and high correlations between parameter estimates. The concept of empirical underidentification is used here to show how these problems can arise, and under what conditions they can be controlled. The discussion is centered around examples showing how small factor loadings, factor correlations near zero, and factor correlations near one can lead to empirical underidentification.
This paper explores long-term partnership benefits of local strategic alliances in knowledge-intensive industries. A structural model of the value continuum is formulated and tested on small and mid-size enterprises in the software industry. Partial least squares path analysis is used to investigate the cause–effect relationships between the foundation values – efficiency and effectiveness – and the innovation value. The results show that the innovation value of localised inter-firm networks originates from costs savings and quality improvements. Conversely, alliance-induced 'speed' benefits (measured by the R&D process's acceleration), which improve flexibility and/or shorten delivery time, have no significant impact on market-based performance. An alliance's time-related benefits may be important to maintain competitive parity, but they do not significantly support competitive advantage, market development and market penetration. Instead, value is created via, for example, an exchange of tacit knowledge and a reduction in transaction costs, and particularly by a reduction in customer service costs.
Much of group and organization research is constrained by either limited sample sizes and/or nascent theoretical development. Wold developed the partial least squares (PLS) data analytical technique to help overcome these and other challenges facing researchers. PLS represents a powerful and effective means to test multivariate structural models with latent variables. Although PLS is used by researchers and practitioners in many scientific disciplines, some misunderstanding remains among group and organization researchers regarding the legitimacy and usefulness of PLS. To help allay these concerns, this article provides a nontechnical primer on PLS and its advantages, limitations, and application to group and organization research using a data set collected in an experiment on the effects of leadership styles and communication format on the group potency of computer-mediated work groups.
Although substantial differences between product quality and service quality have spurred service research for the past 30 years, studies of brand extension success drivers in a services context measure the core driver of parent brand quality, using scales developed for fast moving consumer goods (FMCG). This study instead assesses parent brand quality with a context-specific measure, drawn from service quality research, and analyzes the relative effects of key brand extension success drivers for services. Partial least squares (PLS) modeling offers diagnostic information about the impact of three dimensions of perceived parent brand quality on the perceived service quality of an extension product, a key success metric for service brand extensions. In contrast with previous studies, the dominant success driver is parent brand quality rather than the perceived fit between the parent brand and the extension. Moreover, all three dimensions of parent brand quality constitute distinct drivers that should be considered when managers assess the chances of service brand extension success, with outcome quality having the strongest impact on service brand extension success. An importance performance analysis of the PLS estimates for 27 hypothetical service extensions demonstrates the diagnostic value of this approach and charts a “priority map” for managerial decisions.
When applying multivariate analysis techniques in information systems and social sciences disciplines, such as management information systems (MIS) and marketing, the assumption that the empirical data originate from a single homogeneous population is often unrealistic. When applying a causal modeling approach, such as partial least squares (PLS) path modeling, segmentation is a key issue in coping with the problem of heterogeneity in estimated cause and effect relationships. This paper presents a new PLS path modeling approach which classifies units on the basis of the heterogeneity of the estimates in the inner model. If unobserved heterogeneity significantly affects the estimated path model relationships on the aggregate data level, the methodology will allow homogenous groups of observations to be created that exhibit distinctive path models estimates. Furthermore, the approach will, thus, provide differentiated analytical outcomes that permit more precise interpretations of each segment formed. An application of the procedure on a large dataset in an example of the American customer satisfaction index (ACSI) substantiates the methodology's effectiveness in evaluating PLS path modeling results.
Alongside structural equation modeling (SEM), the complementary technique of partial least squares (PLS) path modeling helps researchers understand relations among sets of observed variables. Like SEM, PLS began with an assumption of homogeneity – one population and one model – but has developed techniques for modeling data from heterogeneous populations, consistent with a marketing emphasis on segmentation. Heterogeneity can be expressed through interactions and nonlinear terms. Additionally, researchers can use multiple group analysis and latent class methods. This chapter reviews these techniques for modeling heterogeneous data in PLS, and illustrates key developments in finite mixture modeling in PLS using the SmartPLS 2.0 package.
As a result of the increasing adoption of private sector firms' values and concepts, non-profit organizations (NPOs) are becoming more and more aware of intangible assets' importance for achieving competitive advantages. Even though reputation can be considered an organization's central intangible asset, there is still no appropriate measurement approach for reputation in this context. In this paper, we identify the dimensions of NPO reputation and develop indices to measure these components. We develop a model by means of a qualitative inquiry and a quantitative study using a large-scale sample from the German general public. We find support for a two-dimensional measurement approach comprising an affective and cognitive component as well as four antecedent constructs (“quality,” “performance,” “organizational social responsibility (OSR),” and “attractiveness”). The results of a second quantitative study in which we examine NPO reputation's relationship with important outcome variables, such as willingness to donate or work as an honorary member, provide support for the measurement approach's stability as well as criterion validity. Furthermore, the results reveal the affective dimension's importance regarding positively influencing donor behavior.
Copyright
Purpose: This paper discusses partial least squares path modeling (PLS), a powerful structural equation modeling technique for research on international marketing. While a significant body of research provides guidance for the use of covariance-based structural equation modeling (CBSEM) in international marketing, there are no subject-specific guidelines for the use of PLS so far. / Methodology/approach: A literature review of the use of PLS in international marketing reveals the increasing application of this methodology. / Findings: This paper reveals the strengths and weaknesses of PLS in the context of research on international marketing, and provides guidance for multi-group analysis. / Originality/value of paper: The paper assists researchers in making well-grounded decisions regarding the application of PLS in certain research situations and provides specific implications for an appropriate application of the methodology.
In this paper, the authors show that PLS path modeling can be used to assess a hierarchical construct model. They pro-vide guidelines outlining four key steps to construct a hier-1 Carol Saunders was the accepting senior editor for this paper. archical construct model using PLS path modeling. This approach is illustrated empirically using a reflective, fourth-order latent variable model of online experiential value in the context of online book and CD retailing. Moreover, the guidelines for the use of PLS path modeling to estimate parameters in a hierarchical construct model are extended beyond the scope of the empirical illustration. The findings of the empirical illustration are used to discuss the use of covariance-based SEM versus PLS path modeling. The authors conclude with the limitations of their study and suggestions for future research.
The literature on structural equation models is unclear on whether and when multicollinearity may pose problems in theory testing (Type II errors). Two Monte Carlo simulation experiments show that multicollinearity can cause problems under certain conditions, specifically: (1) when multicollinearity is extreme, Type II error rates are generally unacceptably high (over 80%), (2) when multicollinearity is between 0.6 and 0.8, Type II error rates can be substantial (greater than 50% and frequently above 80%) if composite reliability is weak, explained variance (2) is low, and sample size is relatively small. However, as reliability improves (0.80 or higher), explained variance 2 reaches 0.75, and sample becomes relatively large, Type II error rates become negligible. (3) When multicollinearity is between 0.4 and 0.5, Type II error rates tend to be quite small, except when reliability is weak, 2 is low, and sample size is small, in which case error rates can still be high (greater than 50%). Methods for detecting and correcting multicollinearity are briefly discussed. However, since multicollinearity is difficult to manage after the fact, researchers should avoid problems by carefully managing the factors known to mitigate multicollinearity problems (particularly measurement error).
In the social science disciplines, the assumption that the data stem from a single homogeneous population is often unrealistic in respect of empirical research. When applying a causal modeling approach, such as partial least squares path modeling, segmentation is a key issue in coping with the problem of heterogeneity in the estimated cause-effect relationships. This article uses the novel finite-mixture partial least squares (FIMIX-PLS) method to uncover unobserved heterogeneity in a complex path modeling example in the field of marketing. An evaluation of the results includes a comparison with the outcomes of several data analysis strategies based on a priori information or k-means cluster analysis. The results of this article underpin the effectiveness and the advantageous capabilities of FIMIX-PLS in general PLS path model set-ups by means of empirical data and formative as well as reflective measurement models. Consequently, this research substantiates the general applicability of FIMIX-PLS to path modeling as a standard means of evaluating PLS results by addressing the problem of unobserved heterogeneity.
Since its first introduction in the Schmalenbach Business Review, Hahn et al.’s (2002) finite mixture partial least squares (FIMIX-PLS) approach to response-based segmentation in variance-based structural equation modeling has received much attention from the marketing and management disciplines. When applying FIMIX-PLS to uncover unobserved heterogeneity, the actual number of segments is usually unknown. As in any clustering procedure, retaining a suitable number of segments is crucial, since many managerial decisions are based on this result. In empirical research, applications of FIMIX-PLS rely on information and classification criteria to select an appropriate number of segments to retain from the data. However, the performance and robustness of these criteria in determining an adequate number of segments has not yet been investigated scientifically in the context of FIMIX-PLS. By conducting computational experiments, this study provides an evaluation of several model selection criteria’s performance and of different data characteristics’ influence on the robustness of the criteria. The results engender key recommendations and identify appropriate model selection criteria for FIMIX-PLS. The study’s findings enhance the applicability of FIMIX-PLS in both theory and practice.
In this chapter it is shown that the PLS-algorithms typically converge if the covariance matrix of the indicators satisfies (approximately) the “basic design”, a factor analysis type of model. The algorithms produce solutions to fixed point equations; the solutions are smooth functions of the sample covariance matrix of the indicators. If the latter matrix is asymptotically normal, the PLS-estimators will share this property. The probability limits, under the basic design, of the PLS-estimators for loadings, correlations, multiple R’s, coefficients of structural equations et cetera will differ from the true values.
But the difference is decreasing, tending to zero, in the “quality” of the PLS estimators for the latent variables. It is indicated how to correct for the discrepancy between true values and the probability limits. We deemphasize the “normality”-issue in discussions about PLS versus ML: in employing either method one is not required to subscribe to normality; they are “just” different ways of extracting information from second-order moments.
We also propose a new “back-to-basics” research program, moving away from factor analysis models and returning to the original object of constructing indices that extract information from high-dimensional data in a predictive, useful way. For the generic
case we would construct informative linear compounds, whose constituent indicators have non-negative weights as well as non-negative loadings, satisfying constraints implied by the path diagram. Cross-validation could settle the choice between various competing
specifications. In short: we argue for an upgrade of principal components and canonical variables analysis.
This chapter illustrates how PLS can be used when investigating causal models with moderators at a higher level of abstraction.
This is accomplished with the presentation of a marketing example. This example specifically investigates the influence of brand personality on brand relationship quality with involvement being a moderator. The literature is reviewed on how to analyze moderational hypotheses with PLS. Considerable work is devoted to the process undertaken to analyze higher order structures.
The results indicate that involvement does moderate the main effects relationship between brand personality and brand relationship quality. This chapter makes a unique contribution and applied researchers will appreciate the descriptive way it is written with regards to analytical process.
Maintaining and increasing visitor satisfaction is a crucial success factor in managing modern, multi-functional stadiums for sports, concerts, shows and other kinds of events. Based on a typical service delivery process when attending an event, this study identifies the relevant factors that influence visitor satisfaction with stadiums. An analysis of this process and its service interfaces by means of direct observation allows us to establish relationships in a structural equation model. Using data from almost 2,500 visitors of a major German multi-purpose stadium, the hypothesised relationships are subsequently tested by means of the partial least squares (PLS) path modelling approach. An importance-performance map-based assessment is used to derive recommendations for improving service interface performance and hence, visitor satisfaction.
Within the Information Systems literature, there has been an emerging interest in the use of formative measurement in structural equation modeling (SEM). This interest is exemplified by descriptions of the nature of formative measurement (e.g., Chin 1998a), and more recently the proper specification offormatively measured constructs (Fetter et al. 2007) as well as application of such constructs (e.g., Barki et al. 2007). Formative measurement is a useful alternative to reflective measurement. However, there has been little guidance on interpreting the results when formative measures are employed. Our goal is to provide guidance relevant to the interpretation of formative measurement results through the examination of the following six issues: multicollinearity; the number of indicators specified for aformatively measured construct; the possible co-occurrence of negative and positive indicator weights; the absolute versus relative contributions made by a formative indicator; nomological network effects; and the possible effects of using partial least squares (PLS) versus covariance-based SEM techniques. We provide prescriptions for researchers to consider when interpreting the results of formative measures as well as an example to illustrate these prescriptions.
Latent variable structural models and the partial least-squares (PLS) estimation procedure have found increased interest since being used in the context of customer satisfaction measurement. The well-known property that the estimates of the inner structure model are inconsistent implies biased estimates for finite sample sizes. A simplified version of the structural model that is used for the Swedish Customer Satisfaction Index (SCSI) system has been used to generate simulated data and to study the PLS algorithm in the presence of three inadequacies: (i) skew instead of symmetric distributions for manifest variables; (ii) multi-collinearity within blocks of manifest and between latent variables; and (iii) misspecification of the structural model (omission of regressors). The simulation results show that the PLS method is quite robust against these inadequacies. The bias that is caused by the inconsistency of PLS estimates is substantially increased only for extremely skewed distributions and for the erroneous omission of a highly relevant latent regressor variable. The estimated scores of the latent variables are always in very good agreement with the true values and seem to be unaffected by the inadequacies under investigation.
Theory development typically focuses on relationships among theoretical constructs, placing little emphasis on relationships between constructs and measures. In most cases, constructs are treated as causes of their measures. However, this causal flow is sometimes reversed, such that measures are viewed as causes of constructs. Procedures have been developed to identify and estimate models that specify constructs as causes or effects of measures. However, these procedures provide little guidance for determining a priori whether constructs should be specified as causes or effects of their measures. Moreover, these procedures address few of the possible causal structures by which constructs and measures may be related. This article develops principles for specifying the direction and structure of relationships between constructs and measures. These principles are illustrated using examples from psychological, sociological, and organizational research.
Two complementary schools have come to the fore in the field of Structural Equation Modelling (SEM): covariance-based SEM and component-based SEM. The first approach has been developed around Karl Joreskog and the second one around Herman Wold under the name 'PLS' (Partial Least Squares). Hwang and Takane have proposed a new component-based SEM method named Generalised Structured Component Analysis. Covariance-based SEM is usually used with an objective of model validation and needs a large sample. Component-based SEM is mainly used for score computation and can be carried out on very small samples. In this research, we will explore the use of ULS-SEM, PLS, GSCA, path analysis on block principal components and path analysis on block scales on customer satisfaction data. Our conclusion is that score computation and bootstrap validation are very insensitive to the choice of the method when the blocks are homogenous.
An approach for capturing unobserved customer heterogeneity in structural equation modeling is proposed based on partial least squares. The method uses a modified finite-mixture distribution approach. An empirical analysis using quality, customer satisfaction and loyalty data for convenience stores illustrates the advantages of the new method vis-à-vis a traditional market segmentation scheme based on well known grouping variables. The results confirm the assumption of heterogeneity in the individuals’ perception of the antecedents and consequences of satisfaction and their relationships. The results also illustrate how the finite-mixture approach complements and provides insights over and above a traditional segmentation scheme.
Variance-based SEM, also known under the term partial least squares (PLS) analysis, is an approach that has gained increasing interest among marketing researchers in recent years. During the last 25 years, more than 30 articles have been published in leading marketing journals that have applied this approach instead of the more traditional alternative of covariance-based SEM (CBSEM). However, although an analysis of these previous publications shows that there seems to be at least an implicit agreement about the factors that should drive the choice between PLS analysis and CBSEM, no research has until now empirically compared the performance of these approaches given a set of different conditions. Our study addresses this open question by conducting a large-scale Monte-Carlo simulation. We show that justifying the choice of PLS due to a lack of assumptions regarding indicator distribution and measurement scale is often inappropriate, as CBSEM proves extremely robust with respect to violations of its underlying distributional assumptions. Additionally, CBSEM clearly outperforms PLS in terms of parameter consistency and is preferable in terms of parameter accuracy as long as the sample size exceeds a certain threshold (250 observations). Nevertheless, PLS analysis should be preferred when the emphasis is on prediction and theory development, as the statistical power of PLS is always larger than or equal to that of CBSEM; already, 100 observations can be sufficient to achieve acceptable levels of statistical power given a certain quality of the measurement model
A generalized form of the cross‐validation criterion is applied to the choice and assessment of prediction using the data‐analytic concept of a prescription. The examples used to illustrate the application are drawn from the problem areas of univariate estimation, linear regression and analysis of variance.
This article examines whether exposure to a company's sponsorship of cultural activities such as “high-brow” arts—including classical music, literature, art exhibitions, and museums—provides a long-term increase in the general public's assessment of corporate reputation. As corporate reputation has been found by previous studies to be composed of two primary dimensions (i.e., the likeability of the firm, the competence of the firm), it is of particular interest to examine whether sponsorship of cultural events affects one or both of these dimensions. A two-dimensional model of image transfer is used as the theoretical basis for a study of more than 3,000 German consumers conducted in collaboration with 10 major multinational companies (e.g., BMW Group and Siemens). Results show that some significant effects of culture-sponsoring activities can be demonstrated for the likeability dimension of corporate reputation and some of its antecedents. However, no significant link between culture sponsorships and consumer perceptions of firm competence is found.
The authors George A. Marcoulides and Carol Saunders have denied the misbelief of some of the researchers in the Information Systems community, who view partial least square (PLS) method as an application that might be used in all cases when the sample size is small. Chin and Newsted determined that small sample sizes do not permit a researcher to detect low valued structural path coefficients until much larger sample sizes. PLS estimates are asymptotically correct in the joint sense of consistency and consistency at large. It is essential that a proposed model meet underlying structural and distributional assumptions for the methodology, and be developed in a manner consistent with all available theoretical and research accumulated knowledge in a given domain.
The broader goal of this paper is to provide social researchers with some analytical guidelines when investigating structural equation models (SEM) with predominantly a formative specification. This research is the first to investigate the robustness and precision of parameter estimates of a formative SEM specification. Two distinctive scenarios (normal and non-normal data scenarios) are compared with the aid of a Monte Carlo simulation study for various covariance-based structural equation modeling (CBSEM) estimators and various partial least squares path modeling (PLS-PM) weighting schemes. Thus, this research is also one of the first to compare CBSEM and PLS-PM within the same simulation study. We establish that the maximum likelihood (ML) covariance-based discrepancy function provides accurate and robust parameter estimates for the formative SEM model under investigation when the methodological assumptions are met (e.g., adequate sample size, distributional assumptions, etc.). Under these conditions, ML-CBSEM outperforms PLS-PM. We also demonstrate that the accuracy and robustness of CBSEM decreases considerably when methodological requirements are violated, whereas PLS-PM results remain comparatively robust, e.g. irrespective of the data distribution. These findings are important for researchers and practitioners when having to choose between CBSEM and PLS-PM methodologies to estimate formative SEM in their particular research situation.
Research into brand extensions has mainly focused on consumers’ extension evaluations without considering an important financial implication: the ability of the extension product to charge a price premium. This study analyzes (1) the extent to which consumers are willing to pay a price premium for the extension product and (2) the impact of potential success drivers on consumers’ attitudes toward the extension and the extension price premium. The results show, for example, that perceived advertising support positively influences consumers’ attitudes toward the extension, but it does not directly affect the magnitude of the brand extension price premium. Furthermore, this study reveals monetary effects associated with these success drivers (i.e., parent brand quality, perceived fit, marketing support for the brand extension, and consumer experience with the extension category), which offer important information regarding how to allocate resources to various success drivers. For example, brand investments that increase perceptions of parent brand quality by one unit (seven-point scale) tend to enhance the brand extension price premium of typical fast moving consumer goods (average price of €2.04 in the study sample) by €.208, all else being equal.
In social and business sciences, the importance of the analysis of interaction effects between manifest as well as latent variables steadily increases. Researchers using partial least squares (PLS) to analyze interaction effects between latent variables need an overview of the available approaches as well as their suitability. This article presents 4 PLS-based approaches: a product indicator approach (Chin, Marcolin, & Newsted, 2003), a 2-stage approach (Chin et al., 2003; Henseler & Fassott, in press), a hybrid approach (Wold, 1982), and an orthogonalizing approach (Little, Bovaird, & Widaman, 2006), and contrasts them using data related to a technology acceptance model. By means of a more extensive Monte Carlo experiment, the different approaches are compared in terms of their point estimate accuracy, their statistical power, and their prediction accuracy. Based on the results of the experiment, the use of the orthogonalizing approach is recommendable under most circumstances. Only if the orthogonalizing approach does not find a significant interaction effect, the 2-stage approach should be additionally used for significance test, because it has a higher statistical power. For prediction accuracy, the orthogonalizing and the product indicator approach provide a significantly and substantially more accurate prediction than the other two approaches. Among these two, the orthogonalizing approach should be used in case of small sample size and few indicators per construct. If the sample size or the number of indicators per construct is medium to large, the product indicator approach should be used.
LISREL and PLS are two different ways of modelling latent variables and their relations to each other within a set of manifest variables. These two models are contrasted with each other. In the special case of two groups of manifest variables the relations that exist between corresponding parameters and latent variables of both types of models are revealed.
This study presents a new algorithm for estimating causal models based on multiblock PLS method. This new algorithm is tested
in a particular post-consumption behavior with the aim of validating a complex system of relations between antecedents of
value, perceived value, satisfaction and loyalty. The results are compared with the classical LVPLS method: both methods support
the proposed structural relations, but the explained variance is slightly higher with the new algorithm.
Along with the development of scientific disciplines, namely social sciences, hypothesized relationships become increasingly more complex. Besides the examination of direct effects, researchers are more and more interested in moderating effects. Moderating effects are evoked by variables whose variation influences the strength or the direction of a relationship between an exogenous and an endogenous variable. Investigators using partial least squares path modeling need appropriate means to test their models for such moderating effects. We illustrate the identification and quantification of moderating effects in complex causal structures by means of Partial Least Squares Path Modeling. We also show that group comparisons, i.e. comparisons of model estimates for different groups of observations, represent a special case of moderating effects by having the grouping variable as a categorical moderator variable. We provide profound answers to typical questions related to testing moderating effects within PLS path models:1.
How can a moderating effect be drawn in a PLS path model, taking into account that the available software only permits direct effects?
2.
How does the type of measurement model of the independent and the moderator variables influence the detection of moderating effects?
3.
Before the model estimation, should the data be prepared in a particular manner? Should the indicators be centered (by having a mean of zero), standardized (by having a mean of zero and a standard deviation of one), or manipulated in any other way?
4.
How can the coefficients of moderating effects be estimated and interpreted?And, finally:
5.
How can the significance of moderating effects be determined?
Borrowing from the body of knowledge on modeling interaction effect within multiple regression, we develop a guideline on how to test moderating effects in PLS path models. In particular, we create a graphical representation of the necessary steps to take and decisions to make in the form of a flow chart. Starting with the analysis of the type of data available, via the measurement model specification, the flow chart leads the researcher through the decisions on how to prepare the data and how to model the moderating effect. The flow chart ends with the bootstrapping, as the preferred means to test significance, and the final interpretation of the model outcomes.
Analysis of Ordinal Categorical Data Alan Agresti Statistical Science Now has its first coordinated manual of methods for analyzing ordered categorical data. This book discusses specialized models that, unlike standard methods underlying nominal categorical data, efficiently use the information on ordering. It begins with an introduction to basic descriptive and inferential methods for categorical data, and then gives thorough coverage of the most current developments, such as loglinear and logit models for ordinal data. Special emphasis is placed on interpretation and application of methods and contains an integrated comparison of the available strategies for analyzing ordinal data. This is a case study work with illuminating examples taken from across the wide spectrum of ordinal categorical applications. 1984 (0 471-89055-3) 287 pp. Regression Diagnostics Identifying Influential Data and Sources of Collinearity David A. Belsley, Edwin Kuh and Roy E. Welsch This book provides the practicing statistician and econometrician with new tools for assessing the quality and reliability of regression estimates. Diagnostic techniques are developed that aid in the systematic location of data points that are either unusual or inordinately influential; measure the presence and intensity of collinear relations among the regression data and help to identify the variables involved in each; and pinpoint the estimated coefficients that are potentially most adversely affected. The primary emphasis of these contributions is on diagnostics, but suggestions for remedial action are given and illustrated. 1980 (0 471-05856-4) 292 pp. Applied Regression Analysis Second Edition Norman Draper and Harry Smith Featuring a significant expansion of material reflecting recent advances, here is a complete and up-to-date introduction to the fundamentals of regression analysis, focusing on understanding the latest concepts and applications of these methods. The authors thoroughly explore the fitting and checking of both linear and nonlinear regression models, using small or large data sets and pocket or high-speed computing equipment. Features added to this Second Edition include the practical implications of linear regression; the Durbin-Watson test for serial correlation; families of transformations; inverse, ridge, latent root and robust regression; and nonlinear growth models. Includes many new exercises and worked examples.
The authors propose a CTA-PLS assessment routine for measurement models. This routine applies confirmatory tetrad analysis (CTA) in a manner which is consistent with partial least squares (PLS) path modeling assumptions. The conceptualization employs a bootstrapping procedure to accomplish an appropriate statistical test examining vanishing tetrads in CTA-PLS. The approach allows distinguishing a formative indicator specification from a reflective indicator specification. Applications using experimental and empirical data demonstrate the usefulness and effectiveness of CTA-PLS. As a means of evaluating PLS path modeling results, the routine assists researchers in avoiding potentially unrepresentative consequences of measurement model misspecification.
PLS-regression (PLSR) is the PLS approach in its simplest, and in chemistry and technology, most used form (two-block predictive PLS). PLSR is a method for relating two data matrices, X and Y, by a linear multivariate model, but goes beyond traditional regression in that it models also the structure of X and Y. PLSR derives its usefulness from its ability to analyze data with many, noisy, collinear, and even incomplete variables in both X and Y. PLSR has the desirable property that the precision of the model parameters improves with the increasing number of relevant variables and observations.This article reviews PLSR as it has developed to become a standard tool in chemometrics and used in chemistry and engineering. The underlying model and its assumptions are discussed, and commonly used diagnostics are reviewed together with the interpretation of resulting parameters.Two examples are used as illustrations: First, a Quantitative Structure–Activity Relationship (QSAR)/Quantitative Structure–Property Relationship (QSPR) data set of peptides is used to outline how to develop, interpret and refine a PLSR model. Second, a data set from the manufacturing of recycled paper is analyzed to illustrate time series modelling of process data by means of PLSR and time-lagged X-variables.
Statistics is a subject of many uses and surprisingly few effective practitioners. The traditional road to statistical knowledge is blocked, for most, by a formidable wall of mathematics. The approach in An Introduction to the Bootstrap avoids that wall. It arms scientists and engineers, as well as statisticians, with the computational techniques they need to analyze and understand complicated data sets.
Two simple estimators are derived here for the means of the random effect model by means of predictive sample reuse. They are applied to two sets of data in the literature and compared with several other procedures. The mixed model is also discussed.
Several issues relating to goodness of fit in structural equations are examined. The convergence and differentiation criteria, as applied by Bagozzi, are shown not to stand up under mathematical or statistical analysis. The authors argue that the choice of interpretative statistic must be based on the research objective. They demonstrate that when this is done the Fornell-Larcker testing system is internally consistent and that it conforms to the rules of correspondence for relating data to abstract variables.
Segmentation in PLS path modeling framework results is a critical issue in social sciences. The assumption that data is collected from a single homogeneous population is often unrealistic. Sequential clustering techniques on the manifest variables level are ineffective to account for heterogeneity in path model estimates. Three PLS path model related statistical approaches have been developed as solutions for this problem. The purpose of this paper is to present a study on sets of simulated data with different characteristics that allows a primary assessment of these methodologies.
- Barry J Babin
- F Joseph
- James S Hair
- Boles
Babin, Barry J., Joseph F. Hair, and James S. Boles (2008), "Publishing Research in Marketing Journals Using Structural Equations Modeling," Journal of Marketing Theory and Practice,
16 (4), 279-285.
Structural Equation Models in Marketing Research: Basic Principles," in Principles of Marketing Research
- Richard P Bagozzi
Bagozzi, Richard P. (1994), "Structural Equation Models in Marketing Research: Basic Principles," in Principles of Marketing Research, Richard P. Bagozzi, ed., Oxford: Blackwell, 317-385.
---, and Youjae Yi (1988), "On the Evaluation of Structural Equation Models," Journal of the Academy of Marketing Science,
16 (1), 74-94.
Formative vs. Reflective Indicators in Measure Development: Does the Choice of Indicators Matter?
- Adamantios Diamantopoulos
- Judy A Siguaw
Diamantopoulos, Adamantios, and Judy A. Siguaw (2000), Introducing LISREL, Thousand Oaks, CA: Sage.
---, and ---(2006), "Formative vs. Reflective Indicators in Measure Development: Does the Choice of Indicators Matter?"
British Journal of Management, 13 (4), 263-282.
---, and Heidi M. Winklhofer (2001), "Index Construction with
Formative Indicators: An Alternative to Scale Development,"
Journal of Marketing Research, 38 (2), 269-277.
---, Petra Riefler, and Katharina P. Roth (2008), "Advancing Formative Measurement Models," Journal of Business Research,
61 (12), 1203-1218.
- G Hult
- M Tomas
- Martin Reimann
- Oliver Schilke
Hult, G. Tomas M., Martin Reimann, and Oliver Schilke (2009),
"Worldwide Faculty Perceptions of Marketing Journals: Rankings, Trends, Comparisons, and Segmentations," globalEDGE
Business Review, 3 (3), 1-10.
Structural Equation Modeling
- Edward E Rigdon
Rigdon, Edward E. (1998), "Structural Equation Modeling," in
Modern Methods for Business Research, G.A. Marcoulides, ed.,
Mahwah, NJ: Lawrence Erlbaum, 251-294.
Correlation and Causation
- Sewall Wright
Wright, Sewall (1921), "Correlation and Causation," Journal of
Agricultural Research, 20 (7), 557-585.