Your fit indices
Copy these from your AMOS, SmartPLS, Mplus or lavaan output.
Sample-size dependent. Many journals no longer ask for it.
—
Indices meeting cut-off
0 / 5
Index by index
How to report it
Before you respecify anything
- Cut-offs are conventions, not laws. Hu and Bentler proposed them under specific conditions. A reviewer may accept .89 with a good justification and reject .91 without one.
- Report every index you computed. Reporting only the flattering ones is the single most common integrity problem in SEM chapters, and it is easy to spot.
- Chi-square is sample-size sensitive. With N above roughly 400 it is almost always significant. That is why the ratio is used instead.
- Modification indices are suggestions, not instructions. Only free a parameter if you can defend it theoretically. "The software suggested it" is not a defence at a viva.
- PLS-SEM is different. If you used SmartPLS, SRMR and NFI apply but CFI, TLI and RMSEA generally do not.
Not sure this is the right calculation for your design? Send us your design and we will tell you which rule applies — at no charge.
Ask about your design