forum.smartpls.com

Dear all,
Please, I did not understand the utility of significance level in bootstrapping procedure. In fact, in the previous version of PLS (i.e., 2.0) this option does not exist and the validity of the model’s relationships is done using T Statistics test. Please, can you clarify this point.

With Kind regards
Wassim

Hi,

In SmartPLS 3, has provided the output P-value with a choice of a one-tailed and two-tailed depends on hypothesis you make.

Greetings,

Hi,

Thank you for your response.

Please, how can I interpret the results from P values? In fact, In PLS 2, T-statistics are larger than 2.58, 1.96 and 1.65 for significance level of 1%, 5% and 10%, respectively.

Many thanks for your help and look forward for your response.

With best regards
Wassim

Hi,

It is easy to interpret with the P-value, depending on the level of significance that you are using and the direction of the hypothesis (eg 5%), means that if the result is < 0.05 then H0 is rejected (two-tailed test).

Greetings,

Hi,

Thank you for your response,

It is not clear for me.

Please Find attached an example. Here, I have used a significance level of 0.01. The P values of these three hypothesis is <0.01, then should I reject these hypothesis?

Many thanks for your help and look forward for your response.

With best regards
Wassim

The setting of the significance level only affects the confidence intervals.
For T and p-values the setting you have done for the significance level is irrelevant (not the direction of the hypothesis one or two-tailed)