MGA result interpretation

[gettu]

Hi all,

I conducted PLS-MGA for two groups and found out that there are no significant differences between path coefficients of the two groups (i used parametric approaches to test the difference)...That means i am not going to reject the null hypothesis. How should i interpret this result? Does this result lead to the conclusion that there is no observed heterogeneity? If so, is this conclusion is going to be meaningful?

Thanks in Advance,
Get

[Hengkov]

Hi,

If the result PLS-MGA not sig this is means not different among your groups cases.

Regards

[nicefreak]

Hi there,

I am running SmartPLS 3 and try to conduct an MGA.
How do I interpret the t-values? According to Sarstedt, Henseler, Ringle (2011), it is not sound to compare if a path coefficient of group A is larger than one of group B and if a different path coefficient of group B is larger than the one of group A at the same time.
Is that still true for the SmartPLS 3 Henseler's MGA? Or is it safe to interpret p values of smaller than .05 and larger than .95 as indicating that the path coefficient of group A is larger than the one of group B (for .05) and the coefficient of B is larger than A (for .95)?

I have tried to switch both groups in the MGA, but the results stay the same!

I have chosen a Bootstrapping significance level of .05 (two tailed). Would I thus interpret the results also at a .05 significance level, or is that then a .1 significance level, because I consider both tails at .05?

Thanks a lot for a clarification!

[nicefreak]

Sorry,

I just found the answer to my question: It says in Smart PLS 3:
Henseler MGA:
This method is a non-parametric significance test for the difference of group-specific results that builds on PLS-SEM bootstrapping results. A result is significant at the 5% probability of error level, if the p-value is smaller than 0.05 or larger than 0.95 for a certain difference of group-specific path coefficients.

[ViWi]

Sorry,

I just found the answer to my question: It says in Smart PLS 3:
Henseler MGA:
This method is a non-parametric significance test for the difference of group-specific results that builds on PLS-SEM bootstrapping results. A result is significant at the 5% probability of error level, if the p-value is smaller than 0.05 or larger than 0.95 for a certain difference of group-specific path coefficients.

Where exactly did you find this quote?

[ViWi]

I found it ;).