SIGN OF T-VALUES IN BOOTSTRAP

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
viswadatta
PLS Expert User
Posts: 139
Joined: Wed Jul 05, 2006 1:43 pm
Real name and title:
Location: Coimbatore, India

SIGN OF T-VALUES IN BOOTSTRAP

Post by viswadatta »

In boot strap, some arrows are to indicate negative values, for eg, environmental uncertainity is to negatively influence organisational effectiveness. In smart PLS I get all values as positive, while in visualPLS I am getting both positive and negative values appropriately. Do I need to apply any settings in bootstrap to get appropriate signs in the t-coefficients?

Regards

Vivek
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Post by cringle »

There are no special settings required in SmartPLS, you always get the correct and appropriate t-values. It should be clear to you that the sign of the t-value does not matter.
viswadatta
PLS Expert User
Posts: 139
Joined: Wed Jul 05, 2006 1:43 pm
Real name and title:
Location: Coimbatore, India

SIGN OF T-VALUES IN BOOTSTRAP

Post by viswadatta »

Thanks, but when we indicate a hypothesis, we need to specify if the relation ship is positive or negative. How do we decide that, if t-values do not have a sign? I understand that the absolute value is to be more than tha cutoff value, say 1.645 (+ or -). Is there any way of proving the nature of the influence?

Regards
Vivek
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Post by cringle »

Dear Vivek,

you use the bootstrapping procedure in PLS to test whether a path coefficient is significantly different from zero. So, if the t-value is higher than your cut-off criterion this is fine and depending on the hypothesized nature of your relationship you get the required evidence. This should be fine and from a statical point of view sufficiently correct. However, we may keep this in mind for the next version...

Cheers
Christian
viswadatta
PLS Expert User
Posts: 139
Joined: Wed Jul 05, 2006 1:43 pm
Real name and title:
Location: Coimbatore, India

sign of relationship

Post by viswadatta »

Thanks, that means we need to look at the coefficient sign , or the construct correlation sign in the ordinary solution to conclude the nature of the relationship, Is it not?

Regards
Charlie_Uganda
PLS Junior User
Posts: 2
Joined: Wed Oct 30, 2019 3:18 pm
Real name and title: Charles Kalinzi, PhD Student

Re: SIGN OF T-VALUES IN BOOTSTRAP

Post by Charlie_Uganda »

Hello community,

Is this in any case similar to getting a t-value of 1.778 (which is more than 1.645) and p-value of 0.077 , returning a non significant value??...can i use the explanation of 95% confidence level to explain this sufficiently??
jmbecker
SmartPLS Developer
Posts: 1282
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: SIGN OF T-VALUES IN BOOTSTRAP

Post by jmbecker »

The t-value threshold for 5% alpha level (or 95% confidence interval) would be 1.96 for a two sided test and 1.645 for a one-sided test. The p-value you are reporting seems to be calculated based on a two-sided test. For a two-sided test the 1.645 t value represents the 10% error level (or 90% confidence interval).
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Post Reply