forum.smartpls.com

Hi all I understand by clicking the latent variables tab after running PLS algorithm, they are the factor scores of each construct for the data set.

All my scales are 7-point Likert scales from 1 to 7. If the path is positive, by multiplying the factor loadings I would expect positive numbers. However I found something strange. Even for one construct which has only two indicators, all positive loadings, the factor score turns out to have negative. Why is that so? My purpose is very simple, just to show a descriptive statistics of what is the average rating on that construct.

If my model is A and B -> C, while C itself has 3-items, what would the latent variable score of C in Smartpls mean then? A combination of the impact of A and B path weights and C indicators, or just C indicators?

Thanks.

Rebecca

All data is routinely standardized in the normal PLS algorithm. Hence, latent variable scores are also standardized. If you want unstandardized LV scores you may use the IPMA, which provides unstandardized LV scores.