forum.smartpls.com

Hello everyone

I have a question: would the comparison of t-values of the respective path coefficients of 2 variables be sufficient enough to claim that one variable has a greater impact than the another (e.g. A has a higher impact on C than B does)?

Since I can not do the Chi -square difference test in Smartpls, what would you suggest me?

many thanks!

No. That is usually not sufficient. You should look at the literature that compares effect sizes in regression and use those approaches.