R square values

Frequently asked questions about PLS path modeling.
Post Reply
Emma Wijnen
PLS Junior User
Posts: 10
Joined: Thu Jun 27, 2013 3:00 pm
Real name and title:

R square values

Post by Emma Wijnen » Wed Jul 10, 2013 1:56 pm

I have a question: where can I find the R2 for the whole structural model? Do I have to calculate it by hand?

I now have 3 R squares for my 3 endogenous variables..however, they will not tell me how good the overall fit of the model is, right?

And I can't use the GoF values, since most of my constructs are formative.

What should I do??

Thanks!

nayabeyes
PLS Expert User
Posts: 74
Joined: Wed Nov 23, 2011 7:34 am
Real name and title:

Re: R square values

Post by nayabeyes » Wed Jul 10, 2013 4:36 pm

Hi,
Go to Calculate=> Run PLS Algorithm then you can see your model (endogenous variables only). Also after running PLS Algorithm go to the Report=> Default Report => Overview here you can see R^2. You don’t need to calculate by hand.

Assessment of structure model (Hair et al., 2013. A primer on PLS-SEM - Book)
1. Check collinearity among the constructs
2. Bootstrapping to assess the significance of the path coefficient
3. R^2
4. Effect size (f^2)
5. Predictive relevance (q^2)
6. Do not use Gof ((Hair et al., 2013-book)
MURAD ALI, Ph.D

Emma Wijnen
PLS Junior User
Posts: 10
Joined: Thu Jun 27, 2013 3:00 pm
Real name and title:

Post by Emma Wijnen » Wed Jul 10, 2013 4:38 pm

Thanks for the quick reply!

But then I get 3 R square values right, for the endogenous variables?

Is there also just one R square value that shows me the goodness of fit of the complete model?

nayabeyes
PLS Expert User
Posts: 74
Joined: Wed Nov 23, 2011 7:34 am
Real name and title:

Post by nayabeyes » Wed Jul 10, 2013 5:05 pm

The final endogenous variable will be your final R^2.

Use the following assessment of structure model (Hair et al., 2013. A primer on PLS-SEM - Book)

1. Check collinearity among the constructs
2. Bootstrapping to assess the significance of the path coefficient
3. R^2
4. Effect size (f^2)
5. Predictive relevance (q^2)
6. Do not use Gof ((Hair et al., 2013-book)
MURAD ALI, Ph.D

Emma Wijnen
PLS Junior User
Posts: 10
Joined: Thu Jun 27, 2013 3:00 pm
Real name and title:

Post by Emma Wijnen » Wed Jul 10, 2013 5:11 pm

Thank you so much, that really helped me a lot! :)

Don't mind me for asking so many question, but how do I calculate the effect size then? Or is it also given?

nayabeyes
PLS Expert User
Posts: 74
Joined: Wed Nov 23, 2011 7:34 am
Real name and title:

Post by nayabeyes » Thu Jul 11, 2013 7:08 am

SmartPLS does not provide it so you have to calculate it manually.
MURAD ALI, Ph.D

FHH
PLS User
Posts: 13
Joined: Fri Sep 06, 2013 5:46 pm
Real name and title:

Re: R square values

Post by FHH » Fri Oct 03, 2014 2:11 pm

1. Check collinearity among the constructs
How exactly is this done? Do I use the LV scores? Standardized or standardized?

jmbecker
SmartPLS Developer
Posts: 1079
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: R square values

Post by jmbecker » Fri Oct 03, 2014 2:13 pm

SmartPLS 3 provides information on the VIF for the inner and outer model.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de

User avatar
Hengkov
PLS Super-Expert
Posts: 1618
Joined: Sun Apr 24, 2011 10:13 am
Real name and title: Hengky Latan
Location: AMQ, Indonesia
Contact:

Re: R square values

Post by Hengkov » Fri Oct 03, 2014 2:15 pm

Hi,

Used VIF for check collinearity among construct. I suggest must < 3.3 for the stable estimation.

Best regards,

FHH
PLS User
Posts: 13
Joined: Fri Sep 06, 2013 5:46 pm
Real name and title:

Re: R square values

Post by FHH » Fri Oct 03, 2014 3:37 pm

Hey Hengkov!
I am using SmartPLS 2. Should I use LV scores (Report > PLS > Calculation results) to test collinearity ALTHOUGH the LV scores are negative in my case (due to negative outer weights)?

User avatar
cringle
SmartPLS Developer
Posts: 812
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: R square values

Post by cringle » Fri Oct 03, 2014 7:00 pm

Hi LV

The LV scores are standardized and thus there are postive and negative values. Yes, use these scores to test collinearity in the structural model. We also explain things in the PLS-SEM book: http://www.sagepub.com/books/Book237345

Best,

Post Reply