PLS-MGA Group Comparison

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Joewin
PLS Junior User
Posts: 6
Joined: Fri May 29, 2015 11:08 am
Real name and title: Joseph Au

PLS-MGA Group Comparison

Post by Joewin »

Dear all,

I'm running PLS-MGA analysis on my defined groups, A and B.

Suppose there is a hypothesis H1. After grouping the data by a control variable and running the PLS-MGA, I have the following results.

1. H1 is supported in completed data set (A+B)
2. H1 is not supported in Group A
3. H1 is supported in Group B

Now, should I still check the p values ( < 0.05 or > 0.95) of the PLS-MGA result for concluding that the grouping has significant effect on H1? or Since H1 is not supported in Group A but supported in Group B, then it is sufficient to say the grouping factor is significant on H1 without checking the p value of PLS-MGA results?

Thanks a lot your help!
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: PLS-MGA Group Comparison

Post by cringle »

We see your point: H1 is not significant in group A but significant in group B and you would like to conclude that H1 sign. differs between groups A and B. Sounds plausible but we still suggest conducting a PLS-MGA or the permutation test and to ensure if the difference between A and B really is sign.

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

Re: PLS-MGA Group Comparison

Post by jmbecker »

A Multi-Group Test is always needed in such a case, because of a statistical phenomenon that sounds paradoxical, but is unfortunately often true: The difference between significant and insignificant must not be itself significant!
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
Joewin
PLS Junior User
Posts: 6
Joined: Fri May 29, 2015 11:08 am
Real name and title: Joseph Au

Re: PLS-MGA Group Comparison

Post by Joewin »

Dear Prof. Ringle and Dr. Becker,

Thanks a lot for your kind explanations.

Regards,
Joseph
Post Reply