Page 1 of 1

T-Test (Bootstrapping) Significance of p-Value

Posted: Sat Jul 15, 2017 5:47 pm
by zypriafl
Dear all,

I have a question regarding the interpretation of the Bootstrapping Results: Does a p-Value higher than 0.95, when using a two-sided t-test for a PLS-Model, shows significance for a path or not?

The SmartPLS-Documentation says this is the case for PLS-Multi-Group Analysis: "[…] if the p-value is smaller than 0.05 or larger than 0.95 for a certain difference of group-specific path coefficients"
https://www.smartpls.com/documentation/ ... es/pls-mga

Is this also true for a Bootstrap Analysis for a PLS-Model using just one data group?

Thank you.

Re: T-Test (Bootstrapping) Significance of p-Value

Posted: Sun Jul 16, 2017 11:49 am
by jmbecker
No. It applies only to the Multi-Group-Analysis as this uses a special p-value calculation that is not based on a t-value.