Hi everyone,
I want to do a multi group analysis with 2 groups and I am not sure what results I should look at: from PLS MGA table or from Parametric test?
Do you have any references for this?
Also, if the effect for one group is not statistically significant, but the difference between groups is, should this difference be reported? Or both groups need to have statistically significant effects?
Anca
MGA
-
- SmartPLS Developer
- Posts: 1282
- Joined: Tue Mar 28, 2006 11:09 am
- Real name and title: Dr. Jan-Michael Becker
Re: MGA
In the best case, the result from the non-parameteric MGA and the parameteric tests agree. In this case you can have high confidence that the effects are significant or nonsignificant. And in most cases they do agree. If they do not agree, you should probably focus on the MGA results as they methodology fits the non-parameteric PLS approach better. You should also consider the permutation approach, which is conceptually a very strong approach and yields reliable results for Multi-Group-Testing.
A good summary of the methods is given in: Sarstedt, M., Henseler, J., & Ringle, C. M. (2011). Multi-group analysis in partial least squares (PLS) path modeling: Alternative methods and empirical results. Advances in International Marketing, 22, 195-218.
You do not need significant effects in both groups.
A good summary of the methods is given in: Sarstedt, M., Henseler, J., & Ringle, C. M. (2011). Multi-group analysis in partial least squares (PLS) path modeling: Alternative methods and empirical results. Advances in International Marketing, 22, 195-218.
You do not need significant effects in both groups.
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
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de