When to use and how to report the results of PLS-SEM
By Joseph F. Hair, Jeffrey J. Risher, Marko Sarstedt, Christian M. Ringle. European Business Review, 2019
22,466 citations recorded by the source corpus.
Purpose 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. Design/methodology/approach 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. Findings 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. Research limitations/implications 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. Originality/value 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.
Subfields: Artificial Intelligence, Information Systems and Management, Organizational Behavior and Human Resource Management
View Paper: https://www.semanticscholar.org/paper/af86ecda37a25a129a3e3f8a03db7db053d8873e
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Christian M. Ringle
- Marko Sarstedt
- Joseph F. Hair
- Jun-Hwa (Jacky) Cheah
- Hiram Ting
- R. Ho
- Thurasamy Ramayah
- S. M. Rasoolimanesh
In Information Systems and Management
- Marko Sarstedt
- Christian M. Ringle
- Joseph F. Hair
- Jun-Hwa (Jacky) Cheah
- Hiram Ting
- Thurasamy Ramayah
- S. M. Rasoolimanesh
- Jorge Matute
In Organizational Behavior and Human Resource Management
- Marko Sarstedt
- Christian M. Ringle
- Joseph F. Hair
- Hiram Ting
- Jun-Hwa (Jacky) Cheah
- Thurasamy Ramayah
- José L. Roldán
- S. M. Rasoolimanesh
Citations in the corpus
- Structural model robustness checks in PLS-SEM (2020, background): “PLS-SEM thus overcomes the apparent dichotomy between explanation, which academic research usually emphasizes, and prediction, which is required to derive managerial implications (Hair et al., 2019; Shmueli et al., 2016, 2018).”
- “Extending the Technology Acceptance Model (TAM) to Predict University Students’ Intentions to Use Metaverse-Based Learning Platforms” (2023, methodology): “The outcomes showed that each construct in the research model acquired an accept - able Cronbech’s Alpha ( > 0.7) (Hair et al., 2019).”
- How can SMEs successfully navigate VUCA environment: The role of agility in the digital transformation era (2022, methodology): “The adoption of the PLS-SEM technique was useful because it helps to yield accurate results in exploratory studies (Hair et al., 2019) and – at the same time – it allows the testing of the model without sample restrictions on the survey (Willaby et al., 2015).”
- Investigating the Impact of User Trust on the Adoption and Use of ChatGPT: Survey Analysis (2023, neutral): “It allows for estimating complex models with several constructs, indicator variables, and structural paths without imposing distributional assumptions on the data [41].”
- Determinants of Intention to Use ChatGPT for Educational Purposes: Findings from PLS-SEM and fsQCA (2023, positive): “We used PLS due to the exploratory nature of the study model, the complexity of the model, and the non-normal distribution of data (Hair et al., 2019; Iranmanesh et al., 2022).”
- Factors versus Composites: Guidelines for Choosing the Right Structural Equation Modeling Method (2019, background): “In order to fulfill the call for rigorous and relevant research, scholars not only need to test theories, but also offer managerial implications, which inherently follow a predictive paradigm (Hair et al., 2019a).”
- Linking Corporate Social Responsibility to Customer Loyalty through Co-Creation and Customer Company Identification: Exploring Sequential Mediation Mechanism (2020, methodology): “The fourth step is to assess the discriminant validity, which is the extent to which a construct is different from the other constructs [65].”
- Facebook advertising, eWOM and consumer purchase intention-Evidence from a collectivistic emerging market (2021, methodology): “Partial least squares (PLS) is considered an appropriate SEM method for the current study due to: (a) the early stage of the theoretical development; (b) the analysis which concerns testing a theoretical framework from a prediction perspective; and (c) the structural model and its relationships bein”