How to draw manifest variables as separate rectangles in SmartPLS?

Feel free to post your requests for new SmartPLS features and other suggestions.
Post Reply
hkeshavarz
PLS Junior User
Posts: 1
Joined: Wed Jun 08, 2022 9:39 am
Real name and title: Hamid Keshavarz, Assistant Professor at Shahid Beheshti Uuniversity, Tehran, Iran

How to draw manifest variables as separate rectangles in SmartPLS?

Post by hkeshavarz »

Dear all,

I hope this email finds you well.

As could be seen in the attached PLS graph, I am trying to construct a manifest variable namely PPB (Privacy Protecting Behavior). The data we gathered for this variable has been binary taken from the settings of the social media users (seven binary items) and not from the survey. As I searched the literature on PLS, we can use almost all data types in our model. However, I failed to understand the mechanism underlying the drawing of this variable. In the Lavaan package of R and Amos as well, it is possible to draw manifests as separate rectangles having no circular shape.

My specific question is how we should treat manifest variables when drawing a model in the SmartPLS? Hair et al (2019) showed that we can use PLS for measuring binary manifest variables as outputs. I would be really grateful if you let me know how I can overcome this challenge. I searched a lot on the internet, but there was no specific answer, especially on drawing the manifest variables.

Kind regards,
Hamid Keshavarz
Attachments
Significance mode 2.00.jpg
Significance mode 2.00.jpg (57.56 KiB) Viewed 565 times
Kligle.png
Kligle.png (238.08 KiB) Viewed 565 times
jmbecker
SmartPLS Developer
Posts: 1205
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: How to draw manifest variables as separate rectangles in SmartPLS?

Post by jmbecker »

SmartPLS 4 allows you to specify rectangles for constructs. However, you still need to represent directly observed variables as single item constructs in the model. This is a requirement of the PLS algorithm. But single item constructs are identical to their single observed measurement item. Thus they basically represent directly observed variables.
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