Examples of PLS for just a measurement model?

[pleeking77]

Hello,

Has anyone used, or have an example of the use of PLS for just a measurement model (versus a measurement model embedded in a larger PLS model)? We would like to use PLS for this purpose but are looking for publications of other who have done this previously.

Thank you!

[Hengkov]

Hi,

After measurement model, next structural model.
See
Chin, W. W. 2010. How to write up and report PLS analyses. In V.E. Vinzi, W. W. Chin, J. Henseler, & H. Wang (Eds.), Handbook of partial least squares: Concepts, methods and applications in marketing and related fields (pp. 655-690).Berlin: Springer. (Chapter 28).

Latan, H and Ghozali, I. Partial Least Squares with SmartPLS, BP UNDIP. (Chapter 14).

Best Regards,
Hengky

[pleeking77]

Thanks so much for sharing these valuable resources on PLS.

Our data doesn't provide insight into the structural model. We have item responses to a depression measure that we want to analyze by racial/ethnic group using a PLS measurement model.

Because of our small group subgroup sizes, PLS is preferable to covariance based SEM. PLS also provides tools to compare the solutions across racial/ethnic groups that make it preferable to Principal Components Analysis (PCA).

Does anyone have any examples of this application of PLS?

Thanks much.

[Hengkov]

Hi Patricia,

See:
Chin, W. W., and Dibbern, J. 2010. An introduction to a permutation based procedure for multigroup PLS analysis: Results of tests of differences on simulated data and a cross cultural analysis of the sourcing of information system services between Germany and the USA. In: V. Esposito Vinzi, W. W. Chin, J. Henseler & H. Wang, et al. (Eds.), Handbook of partial least squares. Concepts, methods and applications (pp. 171–193). Berlin, Heidelberg: Springer.

Eberl, M. 2010. An application of PLS in multi-group analysis: The need for differentiated corporate-level marketing in the mobile communication industry. In V. E. Vinzi, W. W. Chin, J. Henseler, & H. Wang (Eds.), Handbook of partial least squares: Concepts, methods and applications in marketing and related fields (pp. 487-534). Berlin: Springer.

Sarstedt, M., Henseler, J., and Ringle, C.M. 2011. “Multigroup Analysis in Partial Least Squares (PLS) Path Modeling: Alternative Methods and Empirical Result,” Advances in International Merketing (22:1), 195-218.

Henseler, J. 2012. “PLS-MGA: A Non-Parametric Approach to Partial Least Squares-based Multi-Group Analysis,” In W.Gaul et al. (eds.), Chellenges at the Interface of Data Analysis, Computer Science and Optimization, Studies in Classification, Data Analysis and Knowledge Organization, Spinger-Verlag Berlin Heidelberg.

Latan, H., and Ghozali, I. 2012. Partial Least Squares: Concept, Technique and Application SmartPLS, BP UNDIP (Chapter 12).


Best Regards,
Hengky

[Diogenes]

Hi Patricia,

1) With just one LV:
- Do not use SmartPLS.
- Just run PCA and alphas’s Cronbach to assess the unidimensionality and the reliability (SPSS).
- Use summated rating scales (LV = average of the items)
- Use racial/ethnic groups as factor in ANOVA.

2) With 2 or more LV (confirmatory factor analysis with PLS estimation):
- Use SmartPLS.
- The model should have all LV’s connected one with another (as it is done in confirmatory factor analysis), take care to the model be recursive (without feedbacks).
- run the PLS algorithm with “factor weighting scheme”
- Do not use the results of “path coefficients”.
- You could assess outer loadings, AVE, CR, alpha’s Cronbach, crossloadings.
- The LV scores (standardized or unstandardized) could be used in ANOVA.
- I don’t know if multigroup analysis is a good idea, because the path coefficients are not meaningful.

Best regards,

Bido