different result in smartPLS and SPSS

[fahmi]

hi good day everyone...

is it common to have different result in smartPLS and SPSS output with the same regression model?...it is quite confusing because in my smartPLS otput variable A was found not significantly related to dependant variable..however in my SPSS output (the same regression model) variable A become the best predictor in explaining dependant variable...

Anyone can help me with some possible explanation?

[Diogenes]

Hi,
the estimation of unstandardized LV in SmartPLS has a bug (see: viewtopic.php?t=812 ), for this reason, if you used these scores to compare SmartPLS with SPSS, the results are different.

To have SPSS = SmartPLS:
1) Run your model in SmartPLS
2) Copy/paste the standardized LV scores from SmartPLS to SPSS
3) Run the regression
4) beta values in SPSS = path coefficients in SmartPLS

Best regards,

Bido

[ghozali]

hi,
Just run smartpls with standardized value and the result beta coefficient for smartpls equal for beta standardized spss

regards,