The conceptual model I'm working on contains some sociodemographic factors, namely age, gender, income and occupation. These factors contribute to the explanation of the variable " fair trade products perception ", which consists of 5 dimensions measured with 5 point likert scale.
My dilemma resides in the fact that upon using SmartPLS to test the other relationships contained in my model, I find myself unsure whether to continue employing the same method to test the aforesaid relationship( sociodemographic factors__> fair trade products perception ) or i should apply an other method to test it. If it is the case, then i'm much obliged if you point it out for me or provide me with some references that should ease my confusion, if possible of course.
Thank you in advance for the attention given to my question
Hi Meriem.
You can use the SmartPLS in your model. The PLS is more flexible and allow many variables with differents measurement levels. If you have a figure of you model, send to us for more aids.
Best regards
Dirceu
Dear Meriem,
the issue is that the PLS algorithm only allows using metric variables.
Maybe somehow, you could define age, and income as such; but it is very challenging for gender and occupation.
Best regards
SG
Trying to complement what Ganassali presented and focusing on the variables gender and occupation:
I think you can create a model in moderation, where categorical variables could do this moderation between constructs coming from metric variables.
It can get very interesting and reveal other possibilities.
See for example: HAIR, J. F .; HULT, G. T. M .; RINGLE, C. M .; SARSTEDT, M. A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM). Thousand Oaks. Sage Publications, 201.
Also you could do logistic regressions or discriminant analysis with your data, where the categorical variables would be used to guide analysis of differences between us.
Hope this help
Best Regards
Dirceu
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis