As a reviewer, I saw that a manuscript effect size (f square) was found to be greater than 1. The study was conducted in SmartPLS. For this reason, I first asked SmartPLS, but did not get any answers. I was able to find "one" answer on SmartPLS's forum that it might answer a similar question and the answer explained "it has a big effect" (https://forum.smartpls.com/viewtopic.php?t=1902#:~:text=There%20is%20no%20such%20thing,effect%20on%20your%20endogenous%20variable.), but the sources it gives are not satisfactory and the answers are not also satisfactory. I asked google if this is possible, but did not get a very satisfactory answer. And I said "try ChatGPT". Here is the answer;
https://chat.openai.com/share/2b441319-e894-4768-943e-5c09ac05c51b
This answer is also not a very satisfying and technical explanation. Can anyone explain this to me?
Hello Metin,
Cohen's f-squared, as an effect size, represents the proportion of explained to unexplained variance (for the observed effect, factor, or variable). Therefore, as explained variance approaches 1.0 (or 100%), the ratio approaches infinity.
So, yes, these values can exceed 1.0 (which would be the case for 50% explained, 50% unexplained) by a considerable amount, as well as be below 1.0.
Good luck with your work.
According to the first link, the maximum value is 1, although this may include -1 (in correlations). Some effect sizes can exceed 1 (e.g., Cohen's d and beta). According to the same link (the first one you shared), SmartPLS typically uses the coefficient of determination (r-squared), which would not allow for a value greater than 1). However, concerning f square on PLS, I found this link: https://forum.smartpls.com/viewtopic.php?t=1902#:~:text=There%20is%20no%20such%20thing,effect%20on%20your%20endogenous%20variable. Hope this helps!
- Badges
- Science topic
- Similar topics
- Books