PLS algorithm with too few observations

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
cecile
PLS Junior User
Posts: 1
Joined: Sat Jun 30, 2007 11:45 am
Real name and title:

PLS algorithm with too few observations

Post by cecile »

Hello,

I met a problem when clicking on the PLS algorithm icon for calculation.
A window opened and told me that "a singular matrix occured during the estimation of the path coefficient using the path weighting scheme. Setting another weighting scheme could solve the problem".

However, when choosing Centroid or Factor weigthing scheme, I was told that I had too few observations.

However, I have an Excel .csv file with 45 observations.


I thank you for your helpful response.

Cécile

PS : When doing the PLS algorithm with my original file (which contains more than 100 observations), I don't meet any problem.
User avatar
Diogenes
PLS Super-Expert
Posts: 899
Joined: Sat Oct 15, 2005 5:13 pm
Real name and title:
Location: São Paulo - BRAZIL
Contact:

Post by Diogenes »

Hi,

maybe some variable has no variation...

all values almost are the same.

Try to check this.

Best regards.

Bido
Post Reply