latent variable score

This forum is closed, and read-only.
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:

Re: latent variable score

Post by Diogenes »

You are talking about higher order latent variable:
- If the first order LVs have about the same number of indicators, use the repeated indicators approach (see Wetzels et al., 2009, p.181)
- If the number of indicators are very different one of another, it is better to use de two step approach (see Wilson, & Henseler, 2007).

WETZELS, M. et al. Using PLS path modeling for assessing hierarchical construct models: guidelines and empirical illustration. MIS Quarterly, v.33, n.1, p.177-195, March 2009. [p.181]

Wilson, B., & Henseler, J. (2007). Modeling reflective higher-order constructs using three approaches with PLS path modeling: a Monte Carlo comparison. In Australian and New Zealand Marketing Academy (ANZMAC) Conference (pp. 791–800). Retrieved from http://doc.utwente.nl/91758/1/BWilson_2.pdf

Best regards,

Bido
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: latent variable score

Post by jmbecker »

All constructs need indicators in PLS. Therefore you need to use approaches that try to identify the second-order constructs, which are usually either the repeated indicator approach or the two-stage approach.

You can find information on this issue in the following publications:
Becker, J.-M., K. Klein, and M. Wetzels (2012). Formative Hierarchical Latent Variable Models in PLS-SEM: Recommendations and Guidelines, Long Range Planning, 45 (5/6), 359-394.
Kuppelwieser, V., and M. Sarstedt (2014). Applying the Future Time Perspective Scale to Advertising Research, International Journal of Advertising, 33(1), 113-136.
Ringle, C. M., M. Sarstedt, and D. W. Straub (2012). A Critical Look at the Use of PLS-SEM in MIS Quarterly, MIS Quarterly, 36 (1), iii-xiv.
Hair, J. F., Sarstedt, M., Ringle, C. M., & Gudergan, S. P. 2018. Advanced Issues in Partial Least Squares Structural Equation Modeling (PLS-SEM). Thousand Oaks, CA: Sage.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
rathor1072@gmail.com
PLS User
Posts: 16
Joined: Wed May 18, 2016 6:59 pm
Real name and title: shekhu

Re: latent variable score

Post by rathor1072@gmail.com »

How we can interpret the meaning of latent variable scores? What does these scores represent?
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: latent variable score

Post by jmbecker »

PLS is a composite-based method (in contrast to CB-SEM, which is a factor-based method). That means it treats latent variables as composites (i.e., a weighted linear combination of its indicators/manifest variables, as explain earlier in this threat). These latent variable scores or composite scores are the central quantity that define the behavior in composite-based methods such as PLS. They represent the latent variable an approximate their behavior. When using the unstandardized latent variables scores from the IPMA you can take those values as direct estimates of the real value for the latent variable. For example, if you have a 2 on a scale from 1 to 7 on a latent satisfaction variable that would imply a dissatisfied customer.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
NomanMahmood
PLS Junior User
Posts: 3
Joined: Wed Jun 12, 2019 4:52 am
Real name and title: Noman Mahmood

Re: latent variable score

Post by NomanMahmood »

Dear JMBecker,

Can you please guide how many decimal places to take (or round) for Latent Variable Scores to be used as indicators in the model?
(since raw data is integer)
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: latent variable score

Post by jmbecker »

The more the better. SmartPLS calculates with double precision that is 16 decimal places.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Locked