Dears, I ran SmartPLS analysis on my data and I have gotten a high R square value (0.91). Could anyone give an acceptable justification for it? thanks. :)
Unfortunately, there's not enough information in your query for me to give a helpful reply. Others, I suspect, will have the same challenge. Perhaps you could elaborate, by indicating:
1. What are the variables (both manifest/observed and latent) in your model?
2. The R-squared represents variance accounted for in which variable(s)?
What I can tell you is, in some instances, a model that accounts for 91% of variance might be considered extraordinarily good, while in others, that might be considered poor.
dear Walaa Sarayrah The R-squared (R2) value ranges from 0 to 1 with 1 defining perfect predictive accuracy. Since R2 value is adopted in various research disciplines, there is no standard guideline to determine the level of predictive acceptance. Henseler (2009) proposed a rule of thumb for acceptable R2 with 0.75, 0.50, and 0.25 are described as substantial, moderate and weak respectively.
Walaa, as David Morse already pointed out, we definitely need more information concerning your model and your variables in order to provide valuable help.
Dear Walaa, I am not sure what the numbers in the circles representing factors mean. I guess they are some sort of factor reliability?
Could you also provide the unexplained variance of the factor satisfaction? It seems to be obvious that .91 is not the variance explained by the four predictor variables.