Control Variables - Categorical variables

dwilliam · Post by **dwilliam** » Fri May 12, 2006 5:56 pm

Hi all,

Is there a way to control for categorical variable in Smartpls? I need to build a path model, but from prior experience I know that there is an effect via month. Is there a way to get an overall effect for month?

Thanks

schroer · Post by **schroer** » Fri May 12, 2006 6:26 pm

Hi,

I don't think you can control for a variable in SmartPLS out-of-the-box, but one idea that comes to mind is to analyze your data in some other stats software first. E.g., you might regress your outomes on 'month' in SPSS, save the residuals, and then feed those into SmartPLS. Obviously, this way you would have partialled out the time effect.

Good luck,

Joachim

dwilliam · Post by **dwilliam** » Thu Jun 01, 2006 12:55 pm

Partialling out the time effect may be an option. However, I am unsure how that process will actually achieve that effect. I guess I am unsure on how this method would actually work. Any suggestions would be appreciated (any documentation or articles describing this would be good also).