Effect Size and Hypotheses testing

Frequently asked questions about PLS path modeling.
Post Reply
husseins
PLS User
Posts: 13
Joined: Mon Dec 07, 2009 9:08 pm
Real name and title:

Effect Size and Hypotheses testing

Post by husseins »

Dear guys,

I have a question regarding effect size. In my model I found some low effect size. However, these low effect size has a significant relationship. Some other effect size are bigger but they do not have a significant relationship. Please advise me why it can happen?

Kind Regards,
saddas
PLS User
Posts: 19
Joined: Wed Jan 30, 2008 12:54 pm
Real name and title:

Post by saddas »

Did you use the following formula to calculate effect size of a variable X on Y?

R2y (X included) - R2y (X excluded)
______________________________
1 - R2y (X included)
husseins
PLS User
Posts: 13
Joined: Mon Dec 07, 2009 9:08 pm
Real name and title:

Post by husseins »

Yes I used that formula...
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:

Post by Hengkov »

Hi Husein,
Check statistical power analysis.
But I think no problem if effect size is low => significant.
(effect size not relation with result but R-squares => explain variance).
For addition, please check your predictive relevance model.
In general, I know effect size large is mostly significant.

Regards,
Hengky
Post Reply