Reflective-Reflective HOC Question

Frequently asked questions about PLS path modeling.
Post Reply
PLS Junior User
Posts: 1
Joined: Thu Jul 09, 2020 9:05 pm
Real name and title: Dr. Todd Bacile

Reflective-Reflective HOC Question

Post by 84Tigers »

Greetings all. I am working on my first HOC study. Everything looks great in my results, but I do have a question. I am constructing my correlation table along with the AVE values. I want to use the Fornell and Larcker (1981) discriminant validity test to show the square root of the AVE exceeds the correlation with other constructs. My issue, though, is with the second-order construct's high correlation value with one of its first-order constructs. This correlation exceeds the square root of the AVE for the second-order construct. Numbers are listed below. I assume this is fine with HOCs, but I did not know for sure. Does the Fornell and Larcker test apply to the reflective second-order construct like the situation above?

Typically, would I build the correlation table WITHOUT listing the reflective second-order construct? That would solve everything :) Any advice would be appreciated.

The second-order reflective HOC (Construct A) and the two reflective LOCs (Construct B and Construct C). Correlations listed below with the square root of the AVE on the diagonal:

Construct AVE 1 2 3
1) A .62 .79
2) B .76 .92 .87
3) C .61 .63 .27 .78
SmartPLS Developer
Posts: 1129
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Reflective-Reflective HOC Question

Post by jmbecker »

Please read: Sarstedt, M., Hair Jr, J. F., Cheah, J. H., Becker, J. M., & Ringle, C. M. (2019). How to specify, estimate, and validate higher-order constructs in PLS-SEM. Australasian Marketing Journal (AMJ), 27(3), 197-211.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
GoogleScholar: ... AAAJ&hl=de
Post Reply