Huge t-statistic. How come?

Frequently Asked Questions about the SmartPLS software. Please refer to this section first, if you have problems with the software.
Post Reply
pabloem
PLS Junior User
Posts: 1
Joined: Fri May 27, 2016 9:31 am
Real name and title: Pablo E., researcher

Huge t-statistic. How come?

Post by pabloem » Fri May 27, 2016 10:00 am

I have a model where four of my variables come from entiment analysis of text. These are: C2B_PTP, C2B_PTS, C2B_SP, C2B_SS.
For some reason, they are showing me a very very high t-statistics (see figure). Also when running PLS Algorithm, their factor loadings are 1.000.
I already checked the data, and these variables are not proportional. They have correlation, but it's not perfect correlation. So I don't know what could be wrong here.
Anyone know what could be the reason my variables have 1.000 factor loading and huge t-statistic?
Image

jmbecker
SmartPLS Developer
Posts: 879
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Huge t-statistic. How come?

Post by jmbecker » Mon Aug 08, 2016 2:57 pm

Maybe during the import there was a problem with the decimal sign so that you important numbers in a different format.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Ja ... v=hdr_xprf
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de

Umair Azam
PLS Junior User
Posts: 5
Joined: Sun May 14, 2017 2:54 pm
Real name and title: Umair Azam

Re: Huge t-statistic. How come?

Post by Umair Azam » Wed Aug 30, 2017 6:57 pm

Same problem is with me.. my one variable factor loading value is 1 (as pasted below)... what is the reason?
FL-1.jpg
FL-1.jpg (79.44 KiB) Viewed 1559 times
FL-2.jpg
FL-2.jpg (70.99 KiB) Viewed 1559 times

jmbecker
SmartPLS Developer
Posts: 879
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Huge t-statistic. How come?

Post by jmbecker » Thu Aug 31, 2017 7:08 pm

It is a single-indicator construct. Those have per definition in PLS an outer loading of 1, i.e., construct and indicator are per definition equal.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Ja ... v=hdr_xprf
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de

Post Reply