Modelling 2nd order LVs

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Murilo
PLS Junior User
Posts: 2
Joined: Wed Sep 03, 2008 11:48 am
Real name and title:
Location: London

Modelling 2nd order LVs

Post by Murilo »

Hi!

There has been much discussion on how to model 2nd order LVs in this forum. However, I couldn't find an answer to my doubt.

Say you have a 2nd order formative LV (satisfaction) linked to two 1st order reflexive LVs (food quality and service quality). Im my questionnaire, I asked respondents to evaluate their overal satisfaction, which gives me a "indicator" satisfaction.

Can I link this "indicator" satisfaction to the LV satisfaction, instead of using the PCA/Factor analysis or the repetitive indicator approach?

Many Thanks!

Murilo
Murilo Zullo
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:

Post by Diogenes »

Hi Murilo,

two references should be useful:
see the "hybrid approach" of Wilson & Henseler in http://www.anzmac07.otago.ac.nz/anzmacC ... lson_2.pdf

BRUHN, M.; GEORGI, D.; HADWICH, K. Customer equity management as formative second-order construct. Journal of Business Research, Article in press, doi:10.1016/j.jbusres.2008.01.016, 2008.
The 2nd order LV has its own indicators (not repeated approach).

Best regards.

Bido
Murilo
PLS Junior User
Posts: 2
Joined: Wed Sep 03, 2008 11:48 am
Real name and title:
Location: London

Post by Murilo »

Hi Bido,

Thanks very much.

Murilo
Murilo Zullo
cxt7710
PLS Junior User
Posts: 6
Joined: Tue Nov 25, 2008 11:21 am
Real name and title:

Post by cxt7710 »

Hi bido,
Does Smart-pls utilize "the two-stage", "hierarchical components indicators " or "hybrid technique "?
Post Reply