Dear All,
I am a student at Doctoral Program of Accounting in Airlangga University. I have been doing Dissertation to use Partial Least Square (SmartPLS) to test Path Analysis Model.
Is this good enough justification for single indicator LV, i.e. you justify it by using sample sizes=102? How about your opinion?
I will, of course, be happy to help my processing research.
Thank you for your assistance.
Tarjo
Measured Variables
Measured Variables
The best facility
- Diogenes
- PLS Super-Expert
- Posts: 899
- Joined: Sat Oct 15, 2005 5:13 pm
- Real name and title:
- Location: São Paulo - BRAZIL
- Contact:
Hi Tarjo,
1) LV with just one indicator = indicator (measured variable, not latent)
You could use in your model: measured variables and latent variables.
2) sample size depends on the model, use power analysis like is done in multiple regression. A practical rule is about 10 cases/arrow in formative LV or arrows that arrive in a endogenous LV (what was bigger).
Best regards
Bido
1) LV with just one indicator = indicator (measured variable, not latent)
You could use in your model: measured variables and latent variables.
2) sample size depends on the model, use power analysis like is done in multiple regression. A practical rule is about 10 cases/arrow in formative LV or arrows that arrive in a endogenous LV (what was bigger).
Best regards
Bido