Moderation analysis in PLS (SmartPLS4):

Before posting, check our FAQ to see if your question is already covered.
Post Reply
AAljabr
PLS Expert User
Posts: 35
Joined: Wed Jan 06, 2016 11:52 pm
Real name and title: Abdulrahman Aljabr

Moderation analysis in PLS (SmartPLS4):

Post by AAljabr »

Hello,

I have a few comments and questions related to moderation analysis in PLS (SmartPLS4).
1- There is a recommendation (in the PLS literature (Becker et al, 2023) and the general moderation literature (e.g., Dawson, 2014)) that researchers should always interpret the unstandardized coefficient for the interaction term. From my understanding, this recommendation applies regardless of the approach used to measure the independent and moderator variables (e.g., mean-centring, z scores, raw data).
My question is: Does SmartPLS4 provide the unstandardized coefficient for the interaction term?


2- There is a recommendation that, in moderation analysis, the dependent variable should not be mean-centred or z-standardized (Dawson, 2014).
My question is: Does this recommendation apply to the PLS context, and is the application of this recommendation in the PLS context affected by the approach used to measure the independent and moderator variables (e.g., mean-centring, z scores, raw data)?

Thanks

Becker, J. M., Cheah, J. H., Gholamzade, R., Ringle, C. M., & Sarstedt, M. (2023). PLS-SEM’s most wanted guidance. International Journal of Contemporary Hospitality Management, 35(1), 321-346.
Dawson, J. F. (2014). Moderation in management research: What, why, when, and how. Journal of business and psychology, 29(1), 1-19.
jmbecker
SmartPLS Developer
Posts: 1287
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Moderation analysis in PLS (SmartPLS4):

Post by jmbecker »

1. Yes. SmartPLS never standardizes the interaction term and always provides its unstandardized coefficients for them.

2. I am not sure, why it should be a problem to standardize the dependent variable. Dawson does not provide a sufficient argument in his paper why he believes that this is a problem. He simply states that it can be problem without any substantiation.
Important is that you are aware of the type of interpretation in case of standardized variables: you are having changes in standard deviations and not units on the original scale.
If you prefer unstandardized variables you can also do the calculations on unstandardized LV scores using the Groenhold method in SmartPLS 4 using unstandardized in the PLS setting.
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