T statistics interpretation

Feel free to post your requests for new SmartPLS features and other suggestions.
Post Reply
PLS Junior User
Posts: 1
Joined: Sun Mar 08, 2020 9:15 am
Real name and title: Adam Masters

T statistics interpretation

Post by explorer » Sun Mar 08, 2020 9:36 am

Greetings All,

Could you help me regarding T statistics on the Smart PLS 3, please?

as I understand as the first step to run for factor analysis, run the Consistent PLS Algorithms to check loadings, CR, Discriminant Validity, and VIF; and then run the Consistent PLS Bootstrapping to check T statistics and p Values.
Is this the correct procedure?
If yes, then;
what happens if only a number of the T statistics are higher than 1,96 and they show p values as 0,00? Although all factor loadings are almost 0,900, CRs Alphas, and rho values are well above 0,700 and AVEs are above 0,50.

Most of the lines on the table show no p-value nor T statistics?
Similar results appear when tried running regular bootstrapping.

How is it to interpret such case, please?

Anything missing in the process?

Kind Regards,


SmartPLS Developer
Posts: 1110
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: T statistics interpretation

Post by jmbecker » Sun Apr 12, 2020 3:45 pm

What kind of parameter are you looking at, when you assess the t-statistic?
Are you looking at path coefficients? Then it might not be surprising that you have insignificant (p>0.05) coefficients, even if you have very good factor reliability, because it describes the effect from one construct to the other. You may have measured your constructs well, but there is simply no effect.

But without further information on your specific problem it is hard to answer.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de

Post Reply