Latent Variable as Formative Construct objectively measured?

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
sberger
PLS Junior User
Posts: 1
Joined: Thu Jul 06, 2006 11:42 am
Real name and title:

Latent Variable as Formative Construct objectively measured?

Post by sberger »

Hello,

having used SEM and SmartPLS successfully for the first time, I'm unsure at the moment whether I can use it for the following issue:

I'd like to analyze the diffusion of certain groups of metrics in companies.

The idea was to do this by formative constructs, i. e.
  • one LV "diffusion of accounting metrics" (formed by MVs "diffusion of metric 1" and "diffusion of metric 2") and
  • another LV "diffusion of sales metrics" (formed by MVs "diffusion of metric 1" and "diffusion of metric 2").
All MVs would be measured objectively.

Can this be done using latent variable modelling with PLS? Thanks a lot for your help!

Best regards,
Sven
Top
User avatar
Diogenes
PLS Super-Expert
Posts: 899
Joined: Sat Oct 15, 2005 5:13 pm
Real name and title:
Location: São Paulo - BRAZIL
Contact:
Contact Diogenes

Post by Diogenes »

Hi Sven,

at first view the only thing that I will be concerned it will be about multicollinearity of the indicators. I don't know if two or more metrics are always implemented together.

For other issues, I didn't see any problem.

Best regards.

Bido
Top
Post Reply

Return to “Method and application”