Page 1 of 1
How to report lower significant effect size in PLS-SEM (Smart PLS-3)?
Posted: Mon Jun 15, 2020 8:50 pm
by aasafeer
Dear Researchers,
I performed analysis in PLS-SEM and found lower effect size i.e., 0.017 while my relationship is significant. How can I report this? According to Cohen, 1988, less than <0.02 has no effect on relationship. Please advise some reference and advise how to report this result. thank you very much
Re: How to report lower significant effect size in PLS-SEM (Smart PLS-3)?
Posted: Tue Jul 07, 2020 3:01 pm
by jmbecker
If your effect size is very small, your constructs has no substantial contribution to the construct. It does not explain much variance in the target construct. You its effect can be significant (i.e., different from zero). This is the typical difference between relevance and significance. There might be non-zero effects that are not (managerial) relevant because they are so small that they are not important enough to care about. If you increase sample size, even tiny effects become significant.
It is also a question of the field of study. For some effects it might be important to be able to show that they are there, even if they are tiny. For others it is not interesting.
Also note that effects sizes built on f² are relative measures. Relative to the other predictors. If you can explain a lot of variation with your other predictors your focal predictor will eventually become less relevant and effect sizes smaller.