Structural equation modeling (SEM) is widely used to estimate relationships among latent variables and their indicator variables. While different approaches exist, researchers often rely on a single estimation tradition - factor-based or composite-based - despite their distinct assumptions, strengths, and limitations. This practice restricts the rigorous evaluation of structural models, particularly for theories that require both explanatory and predictive assessment. This article introduces a multimethod SEM framework that applies factor-based and composite-based estimators to the same model to assess the robustness of structural paths under alternative conceptual and statistical assumptions. We outline a workflow for implementing multimethod estimation and evaluating convergence and divergence in results. This multimethod SEM framework shifts attention from method allegiance to the empirical performance of the model, thereby improving theoretical inference, predictive assessment, and the overall credibility of SEM-based conclusions.

Most online retailers focus their budgets on customer acquisition, overlooking the long-term value of repeat business. Customer retention can help small and medium-sized enterprises (SMEs) compete in high-consideration categories by providing a solid foundation for a steady path to growth. In this study, we tested the difference in customer value between new and returning visitors by examining web interaction data from 126,335 unique customers of a US-based online alcohol retailer over the course of 12 months. Guided by Cognitive Appraisal Theory, we used session accumulation as the construct through which we could compare customer type. The results revealed that purchase likelihood increased about three times from the first to the sixth session, and later sessions were more predictive of purchase than earlier sessions. We also found that returning users had a significantly higher baseline conversion rate than new customers, as well as a significantly larger increase in conversion with each additional session. Critically, the value premium for returning users was driven by purchase frequency, which was 4.22 times higher than for new customers, rather than by transaction size, which was only 18% higher. As a result, purchase frequency accounted for most of the revenue. For SMEs operating on modest budgets, there is an opportunity cost and a potential advantage in shifting from acquisition to retention.

Marketing analytics has increasingly embraced multi-method approaches to capture the complexity of consumer behavior and organizational phenomena. Among the most prominent are Structural Equation Modeling (SEM), Qualitative Comparative Analysis (QCA), and Artificial Neural Network (ANN), three methodological approaches each grounded in a distinct logic of exploration/theory testing, explanation, and prediction. Despite their complementary strengths, researchers have lacked systematic guidance on how and why their combined application would be beneficial. This research addresses this gap by providing comprehensive guidelines for integrating SEM, QCA, and ANN in a single analytical project. In this article we summarize the theoretical foundations, assumptions, and practical considerations of each method. More specifically, using a synthetic dataset, we demonstrate how SEM is effective for identifying linear and global relationships in a proposed theoretical model. We then explain how QCA can be applied to uncover critical segment-specific “causal recipes” which often remain hidden in SEM. Finally, ANN searches for interactions as well as nonlinear relationships among predictors and which may lead to superior predictive accuracy. By combining these analytical approaches under a single unified analytical framework, this research enhances methodological rigor, mitigates risks of data overfitting and p-hacking, and supports identification of more nuanced insights into complex marketing phenomena. Recommendations for future research directions are also discussed.

This research examines factors influencing employees' use of social media for work-related purposes and its impact on customer relationship performance. The design extends the Technology Acceptance Model (TAM) by integrating employee orientation as a key organizational cultural factor. Using a quantitative methodology, the findings indicate perceived usefulness and perceived ease of use are significant drivers of social media engagement, while employee orientation enhances the effect of perceived usefulness. Results also show work-related social media usage positively impacts customer relationship outcomes. Practical implications including targeted training, clear communication of benefits, and comprehensive social media policies, provide insights regarding how to maximize engagement and mitigate risks.

This study provides a practical guide for handling missing data in partial least squares structural equation modeling (PLS-SEM), a prominent multivariate technique that is widely used in business research. We compare the strengths and limitations of different missing data handling techniques, emphasizing the importance of selecting appropriate methods to enhance the accuracy and reliability of PLS-SEM analyses. Furthermore, we introduce an innovative approach for dealing with not missing at random (NMAR) data by combining imputation with subsequent weighting. By demonstrating the practical effects of various treatment strategies through empirical case studies and a comprehensive simulation study, this research offers meaningful insights and pragmatic guidelines for business researchers dealing with missing data in PLS-SEM.

This special issue comprises a series of methodological advancements and applications of partial least squares structural equation modeling (PLS-SEM) in explaining and predicting new retail market and consumer behaviour habits. A total of five articles were carefully reviewed and selected after several rounds of evaluations. The articles primarily focus on topics related to the combination of multi-methods in PLS-SEM, such as importanceperformance map analysis, necessary condition analysis, multigroup analysis, and prediction in the retail and services market.

A record-high number of sustainable fund closures occurred in 2023, and the first annual net outflows from U.S. sustainability funds. It is widely believed this wave of divestments was primarily related to adjustments in investor priorities. We explore whether there is a relationship between environmental, social, and governance (ESG) risk ratings and stock price movements. Using the momentum oscillator relative strength index (RSI), our research focuses on 440 large companies, that were commonly held in sustainable funds in 2022-2023. The results confirm that environmental and social risks exhibit moderate, significant predictive and explanatory relationships with short-term price movements. Moreover, the findings apply to various methodological approaches, including linear, nonlinear regressions, and supervised machine learning models. Overall, empirical evidence confirms environmental and social risks exhibit both a linear and nonlinear effect on mean and median RSI values. There is an emerging need, therefore, for standardized and more frequent disclosure.

Covariance-based structural equation modeling (CB-SEM) enables researchers to estimate models with hypothesized cause-effect relationships between latent variables (i.e., constructs), each of which is operationalized by several items (i.e., indicators). To conduct CB-SEM analyses, researchers can rely on a range of software applications. However, many of these applications require researchers to engage in sometimes complicated and error-prone programming tasks. While IBM SPSS AMOS provides a graphical user interface (GUI), it does not fully meet the expectations of contemporary software. In order to address these challenges, the statistical SmartPLS 4 software has recently introduced a new CB-SEM module, which improves the user experience through a modern and intuitive graphical interface and comprehensive result reports. This tutorial describes the key CB-SEM analysis steps (i.e., model setup, estimation, and results evaluation) using the SmartPLS software.

Die Partial Least Squares Strukturgleichungsmodellierung (PLS-SEM) hat sich in der wirtschafts- und sozialwissenschaftlichen Forschung als geeignetes Verfahren zur Schätzung von Kausalmodellen behauptet. Dank der Anwenderfreundlichkeit des Verfahrens und der vorhandenen Software ist es auch in der Praxis etabliert.

BACKGROUND:This study explored factors influencing the acceptance of conditionally automated vehicles among Australian drivers by extending the Technology Acceptance Model with the Technology Readiness Index. METHOD:Data from an online survey of 844 participants were analyzed using partial least squares structural equation modeling (PLS-SEM). RESULTS:Perceived usefulness had the strongest direct effect on behavioral intention (0.469, p < 0.001), followed by attitude (0.318, p < 0.001). Innovativeness positively influenced behavioral intention (0.183, p < 0.001), while insecurity had a negative impact (-0.071, p < 0.01). Optimism and discomfort were not significant. Perceived usefulness also had significant indirect effects through attitude (0.156, p < 0.001) and trust (0.072, p < 0.001). Perceived ease of use indirectly influenced behavioral intention through perceived usefulness (0.306, p < 0.001), attitude (0.102, p < 0.001), trust (0.047, p < 0.001), and their combinations. Trust indirectly affected behavioral intention via attitude (0.130, p < 0.001). Perceived security and privacy risks had indirect negative effects through trust and attitude (-0.035, p < 0.001; -0.005, p < 0.05). CONCLUSION:These results suggest that fostering acceptance among less tech-savvy individuals may help promote positive attitudes, increase conditionally automated vehicle adoption, and potentially enhance road safety. PRACTICAL IMPLICATIONS:These findings suggest a need for targeted programs to enhance perceived usefulness and trust while addressing security and privacy concerns, ultimately contributing to safer road systems through the adoption of conditionally automated vehicles.

Artificial intelligence is increasingly being utilized in daily human resource functions, and its implications in the workplace are still to be determined. This paper investigates how employee perceptions of AI usage in the workplace, particularly within HR functions, affect perceived organizational support, perceived human resource effectiveness, psychological well-being, employee engagement, and turnover intentions. We examine these relationships through the lens of Organizational Support Theory, suggesting that when employees perceive an increased use of AI, they can perceive a lack of support from their organization, which can lead to adverse outcomes in the workplace. Our findings provide actionable insights to help companies reinforce a culture of employee trust and support to help mitigate negative employee perceptions in this new AI-enhanced business landscape.

Purpose The purpose of this paper is to assess the appropriateness of equal weights estimation (sumscores) and the application of the composite equivalence index (CEI) vis-à-vis differentiated indicator weights produced by partial least squares structural equation modeling (PLS-SEM). Design/methodology/approach The authors rely on prior literature as well as empirical illustrations and a simulation study to assess the efficacy of equal weights estimation and the CEI. Findings The results show that the CEI lacks discriminatory power, and its use can lead to major differences in structural model estimates, conceals measurement model issues and almost always leads to inferior out-of-sample predictive accuracy compared to differentiated weights produced by PLS-SEM. Research limitations/implications In light of its manifold conceptual and empirical limitations, the authors advise against the use of the CEI. Its adoption and the routine use of equal weights estimation could adversely affect the validity of measurement and structural model results and understate structural model predictive accuracy. Although this study shows that the CEI is an unsuitable metric to decide between equal weights and differentiated weights, it does not propose another means for such a comparison. Practical implications The results suggest that researchers and practitioners should prefer differentiated indicator weights such as those produced by PLS-SEM over equal weights. Originality/value To the best of the authors’ knowledge, this study is the first to provide a comprehensive assessment of the CEI’s usefulness. The results provide guidance for researchers considering using equal indicator weights instead of PLS-SEM-based weighted indicators.

The ongoing scientific discourse surrounding the replication crisis in behavioral research, including management information systems (MIS) research, underscores the importance of innovative and rigorous approaches to theory development and validation. This article proposes the EP-mixed framework, which addresses the necessity of an ontological distinction between explanation and prediction in MIS theories, along with the epistemological challenges associated with conflating exploratory and confirmatory research during the design of robust, replicable theories. EP-mixed refers to theories that explain and predict (i.e., EP theories) developed using a mixed mode that combines the strengths of both exploratory and confirmatory research. The EP-mixed framework guides researchers in selecting appropriate analytical approaches based on their research goals and the type of theory being developed. While it can be applied in conjunction with a broad spectrum of statistical methods to enhance the robustness and replicability of MIS theories, we elaborate on the predictive analytic tools available in partial least squares structural equation modeling (PLS-SEM) as an exemplar for operationalizing the framework.

Die Partial Least Squares Strukturgleichungsmodellierung (PLS-SEM) hat sich in der wirtschafts- und sozialwissenschaftlichen Forschung als geeignetes Verfahren zur Schätzung von Kausalmodellen behauptet. Dank der Anwenderfreundlichkeit des Verfahrens und der vorhandenen Software ist es auch in der Praxis etabliert.

Rapid advancements in artificial intelligence (AI) have significantly transformed how individuals and organizations engage with their work, particularly in research and academia. Universities are urgently developing protocols for student use of large language models (LLMs) for coursework, while peer-reviewed journals and research conferences remain divided on the necessity of reporting AI assistance in manuscript development. This paper examines the diverse perspectives on LLM usage in scholarly research, ranging from concerns about contamination to recognition of its potential benefits. Building on existing literature, we explore guidelines for competitive intelligence (CI) researchers to effectively utilize GPT models, such as ChatGPT4, Scholar GPT, and Consensus GPT, throughout the research cycle. These models, developed by OpenAI, employ generative AI to produce new content based on user prompts, with output quality dependent on input specificity. Despite their recognized potential in literature reviews, qualitative analysis, and data analysis, the full capabilities of GPT models in research remain underutilized. This article provides a comprehensive guide for business researchers to integrate AI language models in planning, structuring, and executing research. Specific guidance is provided for business researchers focused on competitive intelligence.

Purpose Given the positive organizational principles associated with total quality management (TQM) – customer focus, continuous improvement, and process management – one would assume TQM's application is universally beneficial across businesses. Generally, research supports that notion. However, given resource limitations and shallow management teams in small businesses, there are multiple challenges in implementing TQM in small and medium-sized enterprises (SMEs). Therefore, small business leaders should benefit from knowledge linking other management practices to TQM’s positive effect on small firm performance, which enhances these leaders' return on TQM investment. Design/methodology/approach The authors apply partial least squares structural equation modeling (PLS-SEM) to explore TQM’s effect on small business performance and how other management practices enhance that relationship. Specifically, the authors explore how a comprehensive strategic approach (CSA) – a higher-order construct consisting of strategic planning, goal setting, and financial ratio analysis – moderates the relationship between TQM and small business performance. Given the complexity of the authors' model, the application of higher-order constructs, and the exploratory nature of this work, PLS-SEM is well suited for this study. Findings Consistent with prior research, the authors found that TQM (also a higher-order construct, consisting of seven lower-order constructs) positively impacts small firm performance. In addition, the authors found that CSA positively moderates the relationship between TQM and financial performance. Originality/value TQM’s effect on small business performance is enhanced when leaders implement a CSA. In other words, when small business leaders strategically plan, set goals, and analyze financial ratios, TQM's positive effect on firm performance is enhanced. This finding provides business leaders insights for how to maximize the TQM investment return.

Die Partial Least Squares Strukturgleichungsmodellierung (PLS-SEM) hat sich in der wirtschafts- und sozialwissenschaftlichen Forschung als geeignetes Verfahren zur Schätzung von Kausalmodellen behauptet. Dank der Anwenderfreundlichkeit des Verfahrens und der vorhandenen Software ist es auch in der Praxis etabliert.

The call for green innovation necessitates the creation of an ecosystem that is friendly to the environment. Certain environmental regulations and standards are put in place to foster this type of innovation. However, there are many literature debates on the impact of guidelines and management controls on green innovation. Drawing on both the resource-based view (RBV) and dynamic capability theory (DCT), this study investigates the impact of environmental management accounting (EMA) implementation on green process and product innovation, considering the mediating effects of cross-functional coopetition and supplier co-creation. Multi-wave surveys were conducted across 799 Chinese companies. The results show that EMA implementation has a positive effect on both cross-functional coopetition and co-creation. In addition, cross-functional coopetition serves to mediate the relationship between EMA implementation and both green process and product innovation. However, it should be noted that supplier co-creation only serves to mediate the relationship between EMA implementation and green process innovation, rather than green product innovation. Overall, this research adds to the RBV literature by offering a fresh perspective on the role of cross-functional coopetition in situations where resources are shared and conflicts occur simultaneously. Furthermore, the study enhances our understanding of DCT by examining the role of supplier co-creation. This research delves into how companies balance resource availability with environmental adaptability, striking a balance between replication and renewal.

Die Partial Least Squares Strukturgleichungsmodellierung (PLS-SEM) hat sich in der wirtschafts- und sozialwissenschaftlichen Forschung als geeignetes Verfahren zur Schätzung von Kausalmodellen behauptet. Dank der Anwenderfreundlichkeit des Verfahrens und der vorhandenen Software ist es auch in der Praxis etabliert.