forum.smartpls.com

Dear christian! I have a brief question regarding the effect sizes: I have a model with 4 IV and 1 DV, R² is 0.54. It showed that two of the paths are significant, but even these two paths only have effect sizes of 0.11 and 0.12. How can that be explained? Is it dependent on the measurement errors? ...

Dear Forum, if I do a multi-group comparison for the effect of gender, can I calculate the whole model for (1) men and (2) women? That would be only 2 calculations actually. Or do I have to compare each path separately for the gender? For 4 paths, that woulg be 8 calculations. Unfortunately, I can n...

Sorry, this topic was meant to be created under Methodology! Please move it.

Thank you.

Dear Forum, I'm just conducting a multi-group comparison in SmartPLS. I have three groups (age groups) and compare the path coefficients between an independent and a dependent variable. Curiously, when I take the whole sample over all persons, the path is NOT significant. But when I conduct the anal...

Dear forum, I just read the whole correspondence for modelling interaction effects in SmartPLS. The multigroup comparison seems pretty clear to me, but my question is: I have another moderator, namely AGE, which is of course metric scaled. Therefore I guess the interaction term approach is necessary...

As far as I understand the reading and interpretation of the t-distribution table, the sample size depends on the significance level you want to accomplish. Quite logically, you have to obtain more sample cases when gaining for a better level of significance. There is actually no "good" or...