HOC vs. LOC

Research topics can be discussed in this area.
Post Reply
jbhahm
PLS Junior User
Posts: 1
Joined: Wed Apr 22, 2020 3:30 am
Real name and title: Jeongbeom Hahm

HOC vs. LOC

Post by jbhahm »

Hi,

I am working on hypothesized structural model with same measurements but different models (Single order vs. higher order).

My fundamental question is that would it be possible to have two models with same measurements so that I evaluate both? First, overall relationship between higher order construct and the endogenous variables. Second, evaluate the detailed relationship between each dimension (lower order construct) and the endogenous variables.

However, in this case, which path coefficients should be more valuable such as path of lower order construct -> endogenous variable or path of lower order construct -> higher order construct -> endogenous variables?

For your reference, attached please see the hypothesized models.

Thanks

Jeong
Attachments
SM (1) vs (2).png
SM (1) vs (2).png (151.33 KiB) Viewed 53707 times
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: HOC vs. LOC

Post by jmbecker »

I think you should choose one of them. Conceptually you either argue for a higher-order construct or not. You need to decide which model better represents your theory and the underlying data generating (causal) process. Both models will yield different results.
You are also able to assess the impact of each dimension on the final endogenous variable using the total effects of the LOC in a higher-order model.
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
Post Reply