Categorical data

Feel free to post your requests for new SmartPLS features and other suggestions.
Post Reply
PLS Junior User
Posts: 1
Joined: Thu Dec 17, 2015 10:59 am
Real name and title: Salem

Categorical data

Post by 459680 » Thu Dec 17, 2015 11:43 am

Dear All,

I am receiving confusing signal related to whether smart PLS.3 can deal with categorical data. I have a study framework contains 6 variables all of them are categorical (ordinal and nominal) and I can not use Amos as some of the variables have only one indicator.
However, my framework is SEM contains three variable as independent and their indicators are nominal , the second two variable have ordinal and nominal indicators as mediators and the last two are dependent variables and measured by nominal indicators.
Please, could you advise me whether smart PLS.3 is suitable for my study? if yes, please suggest some references to argue my choice.

Kind Regards,

User avatar
SmartPLS Developer
Posts: 791
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)

Re: Categorical data

Post by cringle » Tue Dec 22, 2015 10:32 pm

Please take a look at
Lohmöller, Jan-Bernd. 1989. Latent Variable Path Modeling with Partial Least Squares. Heidelberg: Physica.

You may want to use dummies for all categories. But this is not "standard" PLS-SEM anymore. You need to intepret results similar to logit/probit models.

Best regards
Christian Ringle
pic.png (169.8 KiB) Viewed 5039 times

Post Reply