forum.smartpls.com

Hello all,

I have a short question related to the FIMIX analysis in order to detect/explain unobserved heterogeneity. I have a model with three endogenous reflective constructs that describe three different performance aspects. These constructs are measured by a number of indicators. When running the FIMIX analysis, I come up with two FIMIX segments. I then tried to find an explanatory variable that best matches these FIMIX segments. However, the best match I get is for a variable that is calculated as a mean out of the above mentioned performance indicators (it uses all indicators of the three endogenous constructs and thus, describes the OVERALL performance instead of the three performance aspects).

Is it acceptable to use this overall performance variable as the explanatory variable to explain the FIMIX segments even though the indicators are already part of the PLS model? So far, I had the impression that the explanatory variable must not be part of the model which is why I am not sure what the correct procedure is.

Thanks in advance for any hints.
BR Mara

Usually, the explanatory variable should not be part of the model. Maybe you need to keep searching for other variables. Or based on the description of the segments and some theory and speculations propose a variable that could be a good explanatory variable and should be tested in future research.

Hi,
I am really new in using SmartPLS. I found this post, because I also have problems with interpreting the identified segments by FIMIX.

I tried to find classes of two latent variables. They describe the emotion regulation, one measures the use of adaptive strategies, one of maladaptive strategies. I expected three classes: one with balanced values in both variables, one with higher values in the use of adaptive strategies and one with higher values in th use of maladaptive strategies. Comparing the segmentation of FIMIX with the values of the latent variable for each person, I can't find any interpretable pattern.
How can I compute a latent class analysis in smartPLS without including the explanatory variables (maladaptive and adaptive emotionregulation) in the model?

For information: later I want to compare the groups regarding their relationship to the psychosocial adjustment, wich I will operationalize as another latent variable.

I am really thankful for any help!

__________________________________________________
To avoid misunderstandings because of my limited english knowledge, here again in german.

Ich arbeite mich gerade ganz neu in SmartPLS ein. Diesen Post habe ich gefunden, weil auch ich Probleme damit habe, die von FIMIX identifizierten Segmente zu interpretieren.
Ich habe versucht Klassen über zwei latente Variablen hinweg zu finden. Diese beschreiben die Emotionsregulation, wobei eine die Verwendung adaptiver und eine die Verwendung maladaptiver Strategien erfasst. Ich erwartete drei Klassen: eine mit ausbalancierten Werten in beiden Variablen, eine mit höheren Werten in der Verwendung adaptiver Strategien und eine mit höheren Werten in der Verwendung maladaptiver Strategien. Wenn ich die Zuordnung der Personen über FIMIX mit den Werten in den latenten Variablen vergleiche, kann ich aber kein interpretierbares Muster erkennen.
Wie kann ich denn eine latente Profilanalyse in smartPLS berechnet, ohne die erklärenden Variablen (maladaptive und adaptive Emotionsregulation) mit in das Modell aufzunehmen.

Zur Information: später möchte ich die Gruppen bezüglich ihrer Beziehungen zur psychosozialen Anpassung vergleichen, die ich als weitere latente Variable operationalisere.

Vielen lieben Dank im Voraus!

You may exclude the potential explanatory variables form the model before running FIMIX-PLS. @FIMIX-PLS and segmentation: The book on advanced PLS-SEM issues by Hair et al. (2018) has a chapter on this topic: https://www.smartpls.com/documentation/ ... sem-issues

You may find these articles useful:

• Becker, J.-M., Rai, A., Ringle, C. M., and Völckner, F. (2013). Discovering Unobserved Heterogeneity in Structural Equation Models to Avert Validity Threats., MIS Quarterly, 37(3): 665-694. http://misq.org/discovering-unobserved- ... reats.html

• Hahn, C., Johnson, M. D., Herrmann, A., and Huber, F. (2002). Capturing Customer Heterogeneity Using a Finite Mixture PLS Approach, Schmalenbach Business Review, 54(3): 243-269. https://link.springer.com/article/10.1007/BF03396655

• Hair, J. F., Sarstedt, M., Matthews, L., and Ringle, C. M. (2016). Identifying and Treating Unobserved Heterogeneity with FIMIX-PLS: Part I - Method, European Business Review, 28(1): 63-76. http://www.emeraldinsight.com/doi/abs/1 ... -2015-0094

• Matthews, L., Sarstedt, M., Hair, J. F., and Ringle, C. M. (2016). Identifying and Treating Unobserved Heterogeneity with FIMIX-PLS: Part II – A Case Study, European Business Review, 28(2): 208-224. http://www.emeraldinsight.com/doi/abs/1 ... -2015-0095

• Rigdon, E. E., Ringle, C. M., and Sarstedt, M. (2010). Structural Modeling of Heterogeneous Data with Partial Least Squares, in Review of Marketing Research, N. K. Malhotra (ed.), Sharpe: Armonk, 255-296. http://www.emeraldinsight.com/books.htm ... id=1896306

• Rigdon, E. E., Ringle, C. M., Sarstedt, M., and Gudergan, S. P. (2011). Assessing Heterogeneity in Customer Satisfaction Studies: Across Industry Similarities and Within Industry Differences, Advances in International Marketing, (22): 169-194. http://www.emeraldinsight.com/books.htm ... id=1947689

• Ringle, C. M., Sarstedt, M., and Mooi, E. A. (2010). Response-Based Segmentation Using Finite Mixture Partial Least Squares: Theoretical Foundations and an Application to American Customer Satisfaction Index Data, Annals of Information Systems, (8): 19-49. http://www.springer.com/cda/content/doc ... 794-c1.pdf

• Sarstedt, M., Becker, J.-M., Ringle, C. M., and Schwaiger, M. (2011). Uncovering and Treating Unobserved Heterogeneity with FIMIX-PLS: Which Model Selection Criterion Provides an Appropriate Number of Segments?, Schmalenbach Business Review, 63(1): 34-62. http://www.sbr-online.de/pdfarchive/ein ... 34-062.pdf

• Sarstedt, M., and Ringle, C. M. (2010). Treating Unobserved Heterogeneity in PLS Path Modelling: A Comparison of FIMIX-PLS with Different Data Analysis Strategies, Journal of Applied Statistics, 37(8): 1299-1318. http://www.tandfonline.com/doi/pdf/10.1 ... 0903030213

• Sarstedt, M., Ringle, C. M., and Gudergan, S. P. (2016). Guidelines for Treating Unobserved Heterogeneity in Tourism Research: A Comment on Marques and Reis (2015), Annals of Tourism Research, 57(March): 279-284. http://www.sciencedirect.com/science/ar ... 8315001462

• Sarstedt, M., Ringle, C. M., & Hair, J. F. (2017). Treating Unobserved Heterogeneity in PLS-SEM: A Multi-Method Approach. In R. Noonan & H. Latan (Eds.), Partial Least Squares Structural Equation Modeling: Basic Concepts, Methodological Issues and Applications (pp. 197-217). Heidelberg: Springer. https://link.springer.com/chapter/10.10 ... -64069-3_9

• Sarstedt, M., Schwaiger, M., and Ringle, C. M. (2009). Do We Fully Understand the Critical Success Factors of Customer Satisfaction with Industrial Goods? - Extending Festge and Schwaiger’s Model to Account for Unobserved Heterogeneity, Journal of Business Market Management, 3(3): 185-206. http://link.springer.com/article/10.100 ... 009-0023-7