Question about simple slope test

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
4rain
PLS Junior User
Posts: 3
Joined: Tue Aug 09, 2016 11:04 am
Real name and title: Tao,Ran. PhD student of Marketing

Question about simple slope test

Post by 4rain »

I need to conduct simple slope test with smartpls3 and related topics within this forum are 1:Partial derivate plots of interactions;2:Interaction Effect Term and Regression Handling. Both topics mentioned, by software developers, simple slop test is a function of new release. But both topics did not offer instruction of how to achieve such function and I cannot find the help menu within smartpls3. Could anyone provide me with necessary info, the better a step-by-step tutorial?
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: Question about simple slope test

Post by cringle »

Just run a moderator analysis (right-click on a target construct, select the moderator option, create the interaction term, run the analysis). In the results report, you find a simple slope plot (under results, last entry) - but only when you run a moderator analysis.

You may find the chapter on moderation in the PLS-SEM book useful: https://www.smartpls.com/documentation/ ... on-pls-sem

Best
Christian
krismurphy01
PLS Junior User
Posts: 8
Joined: Tue Jan 20, 2015 2:34 pm
Real name and title: Kris Murphy

Re: Question about simple slope test

Post by krismurphy01 »

Hello,

Does anyone know how to run a "simple slope analysis" using the consistent PLS method? I see that the test can be ran using the traditional method (see below) but I am not certain how the slope analysis is run for the consistent method (version 3.24).

I have the newest version of the book, but I have yet to find an answer to this question.

Calculate -> Partial Least Squares Algorithm -> Final Results -> Simple Slope Analysis

Kris
jmbecker
SmartPLS Developer
Posts: 1282
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Question about simple slope test

Post by jmbecker »

The procedure for PLSc would be the same as for normal PLS. It is a good hint that we should also implement this for PLSc.

Until then, you could just create the plot yourself:
The slope of the line for Moderator at Mean is the simple effect of your dependent variable.
The slope of the line for Moderator at -1 SD is the simple effect of your dependent variable minus the interaction effect.
The slope of the line for Moderator at +1 SD is the simple effect of your dependent variable plus the interaction effect.
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
nina_04
PLS Junior User
Posts: 2
Joined: Mon May 11, 2020 8:54 am
Real name and title: Nina Mac

Re: Question about simple slope test

Post by nina_04 »

Dear Professor Becker,

I have a question regarding your answer.
jmbecker wrote: Sun Apr 23, 2017 8:54 am Until then, you could just create the plot yourself:
The slope of the line for Moderator at Mean is the simple effect of your dependent variable.
The slope of the line for Moderator at -1 SD is the simple effect of your dependent variable minus the interaction effect.
The slope of the line for Moderator at +1 SD is the simple effect of your dependent variable plus the interaction effect.
Does it mean that e.g. if the moderator is a dummy variable where 0=old population and 1=young population, that -1 SD = old population and +1 SD =young population in the simple slope analysis? Or is that incorrect?

Thanks in advance!
Post Reply