Search results

Partial least squares (PLS) has been introduced as a “causal-predictive” approach to structural equation modeling (SEM), designed to overcome the apparent dichotomy between explanation and prediction. However, while researchers using PLS-SEM routinely stress the predictive nature of their analyses, model evaluation assessment relies exclusively on metrics designed to assess the path model’s explanatory power. Recent research has proposed PLSpredict, a holdout sample-based procedure that generates case-level predictions on an item or a construct level. This paper offers guidelines for applying PLSpredict and explains the key choices researchers need to make using the procedure.

The authors discuss the need for prediction-oriented model evaluations in PLS-SEM and conceptually explain and further advance the PLSpredict method. In addition, they illustrate the PLSpredict procedure’s use with a tourism marketing model and provide recommendations on how the results should be interpreted. While the focus of the paper is on the PLSpredict procedure, the overarching aim is to encourage the routine prediction-oriented assessment in PLS-SEM analyses.

The paper advances PLSpredict and offers guidance on how to use this prediction-oriented model evaluation approach. Researchers should routinely consider the assessment of the predictive power of their PLS path models. PLSpredict is a useful and straightforward approach to evaluate the out-of-sample predictive capabilities of PLS path models that researchers can apply in their studies.

Future research should seek to extend PLSpredict’s capabilities, for example, by developing more benchmarks for comparing PLS-SEM results and empirically contrasting the earliest antecedent and the direct antecedent approaches to predictive power assessment.

This paper offers clear guidelines for using PLSpredict, which researchers and practitioners should routinely apply as part of their PLS-SEM analyses.

This research substantiates the use of PLSpredict. It provides marketing researchers and practitioners with the knowledge they need to properly assess, report and interpret PLS-SEM results. Thereby, this research contributes to safeguarding the rigor of marketing studies using PLS-SEM.

Partial least squares structural equation modeling (PLS-SEM) has become popular in the information systems (IS) field for modeling structural relationships between latent variables as measured by manifest variables. However, while researchers using PLS-SEM routinely stress the causal-predictive nature of their analyses, the model evaluation assessment relies exclusively on criteria designed to assess the path model's explanatory power. To take full advantage of the purpose of causal prediction in PLS-SEM, it is imperative for researchers to comprehend the efficacy of various quality criteria, such as traditional PLS-SEM criteria, model fit, PLSpredict, cross-validated predictive ability test (CVPAT) and model selection criteria.

A systematic review was conducted to understand empirical studies employing the use of the causal prediction criteria available for PLS-SEM in the database of Industrial Management and Data Systems (IMDS) and Management Information Systems Quarterly (MISQ). Furthermore, this study discusses the details of each of the procedures for the causal prediction criteria available for PLS-SEM, as well as how these criteria should be interpreted. While the focus of the paper is on demystifying the role of causal prediction modeling in PLS-SEM, the overarching aim is to compare the performance of different quality criteria and to select the appropriate causal-predictive model from a cohort of competing models in the IS field.

The study found that the traditional PLS-SEM criteria (goodness of fit (GoF) by Tenenhaus, R2 and Q2) and model fit have difficulty determining the appropriate causal-predictive model. In contrast, PLSpredict, CVPAT and model selection criteria (i.e. Bayesian information criterion (BIC), BIC weight, Geweke–Meese criterion (GM), GM weight, HQ and HQC) were found to outperform the traditional criteria in determining the appropriate causal-predictive model, because these criteria provided both in-sample and out-of-sample predictions in PLS-SEM.

This research substantiates the use of the PLSpredict, CVPAT and the model selection criteria (i.e. BIC, BIC weight, GM, GM weight, HQ and HQC). It provides IS researchers and practitioners with the knowledge they need to properly assess, report on and interpret PLS-SEM results when the goal is only causal prediction, thereby contributing to safeguarding the goal of using PLS-SEM in IS studies.

To determine how to best deploy the Triple-A supply chain (SC) capabilities (AAA-agility, adaptability and alignment) to improve competitive advantage (CA) by identifying the Triple-A SC model with the highest CA predictive capability.

Assessment of in-sample and out-of-sample predictive capacity of Triple-A-CA models (considering AAA as individual constructs) to find which has the highest CA predictive capacity. BIC, BIC-Akaike weights and PLSpredict are used in a multi-country, multi-informant, multi-sector 304 plant sample.

Greater direct relationship model (DRM) in-sample and out-of-sample CA predictive capacity suggests DRM's greater likelihood of achieving a higher CA predictive capacity than mediated relationship model (MRM). So, DRM can be considered a benchmark for research/practice and the Triple-A SC capabilities as independent levers of performance/CA.

DRM emerges as a reference for analysing how to trigger the three Triple-A SC levers for better performance/CA predictive capacity. Therefore, MRM proposals should be compared to DRM to determine whether their performance is significantly better considering the study's aim.

Results with our sample justify how managers can suitably deploy the Triple-A SC capabilities to improve CA by implementing AAA as independent levers. Single capability deployment does not require levels to be reached in others.

First research considering Triple-A SC capability deployment to better improve performance/CA focusing on model's predictive capability (essential for decision-making), further highlighting the lack of theory and contrasted models for Lee's Triple-A framework.

The purpose of this paper is to provide a comprehensive, yet concise, overview of the considerations and metrics required for partial least squares structural equation modeling (PLS-SEM) analysis and result reporting. Preliminary considerations are summarized first, including reasons for choosing PLS-SEM, recommended sample size in selected contexts, distributional assumptions, use of secondary data, statistical power and the need for goodness-of-fit testing. Next, the metrics as well as the rules of thumb that should be applied to assess the PLS-SEM results are covered. Besides presenting established PLS-SEM evaluation criteria, the overview includes the following new guidelines: PLSpredict (i.e., a novel approach for assessing a model’s out-of-sample prediction), metrics for model comparisons, and several complementary methods for checking the results’ robustness.

This paper provides an overview of previously and recently proposed metrics as well as rules of thumb for evaluating the research results based on the application of PLS-SEM.

Most of the previously applied metrics for evaluating PLS-SEM results are still relevant. Nevertheless, scholars need to be knowledgeable about recently proposed metrics (e.g. model comparison criteria) and methods (e.g. endogeneity assessment, latent class analysis and PLSpredict), and when and how to apply them to extend their analyses.

Methodological developments associated with PLS-SEM are rapidly emerging. The metrics reported in this paper are useful for current applications, but must always be up to date with the latest developments in the PLS-SEM method.

In light of more recent research and methodological developments in the PLS-SEM domain, guidelines for the method’s use need to be continuously extended and updated. This paper is the most current and comprehensive summary of the PLS-SEM method and the metrics applied to assess its solutions.

Intrapreneurial ability (IA) of employees strengthens an organization's internal as well as external growth. Employees' IA makes innovation a continuous practice and augments organization's intellectual capital (IC). This intellectual capital-based intrapreneurial ability (ICIA) helps professionals to effectively handle changes in the business ecosystem by creating innovative solutions. The onus of assessing and inculcating ICIA is a joint responsibility of both academia and industry. In academia, teacher as a servant leader (TASL) contributes towards building ICIA of working professionals (WP) by enhancing their self-efficacy (SE). The paper aims to strengthen the industry–academia interface by analyzing the role of TASL and SE in influencing the ICIA of WP.

Using a stratified sampling technique, data from 387 WP is analyzed on SmartPLS-4 to study the interrelationship between the stated constructs and the role of SE as a mediator between TASL and ICIA. PLSpredict is used to study the predictive relevance of the proposed model.

High R² = 0.654 shows that 65% of ICIA is determined by SE and TASL; reflecting model's robustness. SE partially mediates the relationship between TASL and ICIA. Results reported a higher ICIA of male WP than their female counterpart. The results indicate the low predictive accuracy of the model.

The proposed model of industry–academia partnership allows assessment of ICIA for enhancing corporate value in the present gig economy. The study also highlights the relevance of ICIA, particularly, for developing economies. In knowledge-driven economy, exploring the new ICIA will help organizations to draft a more robust performance measurement system.

This unique industry–academia partnership studies the role of TASL towards enhancing SE and ICIA of WP. The novelty of ICIA would enrich and provide a new perspective in IA literature. Additionally, the study also examines the role of gender in the ICIA of WP.

The purpose of this study is to clarify theory and identify factors that could explain the level of fintech continuance intentions with an expectation confirmation model that integrates self-efficacy theory.

With data collected from 753 fintech users, this study applies partial least square structural equation modeling to compare and select the research model with the most predictive power.

The results show that financial self-efficacy, technological self-efficacy and confirmation positively affect perceived usefulness. Among these factors, financial self-efficacy and technological self-efficacy have both direct and indirect effects through confirmation on perceived usefulness. Perceived usefulness and confirmation are positively related to satisfaction. Finally, perceived usefulness and satisfaction positively influence fintech continuance intentions.

To the best of our knowledge, this is one of the earliest studies that investigates the effect of domain-specific self-efficacy on fintech continuance intentions, which enriches the existing research on fintech and deepens our understanding of users' fintech continuance intentions. We distinguish between financial self-efficacy and technological self-efficacy and specify the relationship between self-efficacy and continuance intentions. Moreover, this study highlights the importance of assessing a model's predictive power using the PLSpredict technique and provides a reference for model selection.

The purpose of this paper is to assess the effect of two promotional methods, namely, celebrity endorsed advertisement and selfie promotion, on customers’ decision-making processes using the AISAS model.

A within-subject experimental design was used to observe how young adults in Malaysia would respond to two promotional methods about a new seafood restaurant. A total of 180 responses were collected using a structured questionnaire. Data were assessed and analysed using partial least squares structural equation modelling.

The results show that while celebrity endorsed advertisement remains relevant to customer’s decision-making processes, the effect of selfie promotion is comparable to celebrity endorsement. The sequential mediation for both models is found to be significant, but the AISAS model with selfie promotion produces better in-sample prediction (model selection criteria) and out-of-sample prediction (PLSpredict) compared to celebrity endorsed advertisement, thus suggesting its better representation to reality.

Despite being limited to young adults in Malaysia and a particular product, the study is essential to understanding the effect of celebrity endorsed advertisement and selfie promotion on decision-making processes.

The study provides insights into how business organisations could exploit the advancement of communication technology to encourage selfie behaviour to promote their products in an innovative and competitive manner.

The assessment of the effect of celebrity endorsed advertisement and selfie promotion on decision-making processes using PLSpredict and model selection criteria articulates the relevance of selfie as a promotional tool. It also provides an alternative technique for conducting model comparison research.

This research aims to examines the impact of micro-level corporate social responsibility (CSR) practices on employee engagement within the public accounting firm setting.

This research uses a quantitative approach with a survey instrument as the data collection tool. A total of 269 complete responses were collected from employees working in the public accounting firms. Micro-level CSR practices were analysed with a hierarchical component model (HCM) in partial least square structural equation modelling (PLS-SEM) to examine the influence of such practices on employee engagement. A predictive performance metric was applied to assess the out-of-sample prediction.

This study uncovers a positive and significant relationship between micro-level CSR practices and employee engagement. Furthermore, the PLSpredict results indicate that the current model possesses high predictive power with all indicators in the PLS-SEM analysis demonstrating lower root mean squared error (RMSE) values compared to the naïve linear regression model benchmark.

While the methods applied in this analysis are at the frontier of CSR research, the present study has not explored the heterogeneity amongst groups of respondents and size of accounting firms. Sampling weight adjustment for the purposes of representativeness was not used in the current research. These could be the subject of future work in this area.

These research findings shed light on the positive manifestation effect of micro-level CSR practices at firm level as well as individual level. Through micro-level CSR practices, firms can reap the benefits of enhanced employee engagement, which leads to productive workforce while also facilitating increased employees’ intrinsic job satisfaction.

Micro-level CSR practices address the needs of the millennium workforce, whereby employees are no longer solely focussed on pay checks as their compensation. Employees are seeking out employers whose CSR practices appeal to their social conscience. Micro-level CSR practices meet the needs of the contemporary workforce yet enable companies to attract and retain skilled employees.

The originality of this research is attributed to the vigorous statistical analysis by the use of HCMs and PLSpredict in PLS-SEM context for the assessment of predictive performance. Also, micro-level CSR practices are conceptualised in HCM for parsimonious purpose.

Purpose of This Chapter: This study explores the positive chain effects of Employee-Centered CSR (ECCSR) in harmonizing the current challenges of The Great Resignation from the perspective of employees’ well-being.

Design / Methodology / Approach: The quantitative approach was used to test the proposed research model by using a self-responded questionnaire. Purposive judgemental sampling was applied to qualify the respondents based on the criteria that they are gainfully employed now and during the pandemic. The responses gathered were analyzed using structural equation modelling (SEM).

Findings: The findings show that ECCSR significantly and positively influences employees’ well-being, specifically workplace well-being (β = 0.793), social well-being (β = 0.761), psychological well-being (β = 0.712), and subjective well-being (β = 0.611). The PLSpredict results reveal that the proposed research model possesses the predictive relevance of ECCSR in reflecting the reality of employees’ well-being.

Research Limitations: The data were collected in the post-pandemic phase to capture the employees’ state of mind. Hence, the findings may not represent the normal business cycle challenges.

Practical Implications: The empirical evidence suggests that depressing organizations to consider implementing ECCSR for employees’ well-being which in turn enables the organizations to navigate through turbulent times a little easier.

Originality: The novelty of this study is attributed to the positive and detailed findings of ECCSR in the context of employee well-being for organizational resilience.