Consistent PLS-SEM
Consistent PLS-SEM (PLSc-SEM) is a correction procedure applied to the results of the standard PLS-SEM algorithm. It adjusts the correlations among reflectively measured constructs so that composite-based PLS-SEM estimates become consistent with those of a common factor model (Dijkstra, 2010, 2014; Dijkstra & Henseler, 2015; Dijkstra & Schermelleh-Engel, 2014). Researchers use PLSc-SEM when they want composite-based estimation that mimics common-factor results for reflectively specified constructs, effectively bridging PLS-SEM and CB-SEM. The correction builds on Nunnally's (1978) well-known correction-for-attenuation formula.
PLSc-SEM Settings in SmartPLS
| Setting | Description |
|---|---|
| Initial calculations | Choose whether the initial PLS path model is used as specified, or whether all latent variables (LVs) are connected to generate latent variable scores when running the PLS-SEM algorithm. Dijkstra and Henseler (2015) advise using connections between all LVs to obtain more stable latent variable score estimates. |
No additional parameter specifications are required for the correction that PLSc-SEM performs on the results of the basic PLS-SEM algorithm. However, the parameter settings for the underlying PLS-SEM algorithm remain important and should be checked before running PLSc-SEM.
Frequently Asked Questions
What does PLSc-SEM correct for?
PLSc-SEM corrects the correlations of reflectively measured constructs so that composite-based PLS-SEM results become consistent with those of a common factor model.
When should I use PLSc-SEM instead of standard PLS-SEM?
Use PLSc-SEM when you want composite-based estimation that approximates common-factor model results for reflectively specified constructs, bridging PLS-SEM and CB-SEM estimation logics.
Does PLSc-SEM require additional settings in SmartPLS?
No. Beyond the "Initial calculations" option, no additional parameter specifications are required for the PLSc-SEM correction itself. The settings of the underlying PLS-SEM algorithm, however, are still important and should be checked.
What does the "Initial calculations" setting control?
It determines whether the initial PLS path model is used as specified, or whether all latent variables are connected to generate latent variable scores. Connecting all LVs is recommended for more stable score estimation.
What is the statistical basis for the PLSc-SEM correction?
The correction builds on Nunnally's (1978) correction-for-attenuation formula and on the consistent PLS approach developed by Dijkstra and colleagues (Dijkstra, 2010, 2014; Dijkstra & Henseler, 2015; Dijkstra & Schermelleh-Engel, 2014).
Related SmartPLS Methods
- PLS-SEM algorithm
- Weighted PLS algorithm
- PLS-PCA
- Covariance-based structural equation modeling (CB-SEM)
References
- Dijkstra, T. K. (2010). Latent variables and indices: Herman Wold's basic design and partial least squares. In V. Esposito Vinzi, W. W. Chin, J. Henseler, & H. Wang (Eds.), Handbook of partial least squares: Concepts, methods and applications (pp. 23–46). Springer.
- Dijkstra, T. K. (2014). PLS' Janus face – response to Professor Rigdon's 'Rethinking Partial Least Squares Modeling: In Praise of Simple Methods'. Long Range Planning, 47(3), 146–153.
- Dijkstra, T. K., & Henseler, J. (2015). Consistent partial least squares path modeling. MIS Quarterly, 39(2), 297–316.
- Dijkstra, T. K., & Schermelleh-Engel, K. (2014). Consistent partial least squares for nonlinear structural equation models. Psychometrika, 79(4), 585–604.
- Nunnally, J. C. (1978). Psychometric theory. McGraw-Hill.
- More literature ...
Cite correctly
Please always cite the use of SmartPLS!
Ringle, Christian M., Wende, Sven, & Becker, Jan-Michael. (2024). SmartPLS 4. Bönningstedt: SmartPLS. Retrieved from https://www.smartpls.com
