ØBaseline Comparisons
The Baseline Comparisons table can be found under: View → Text Output → Model fit → Baseline Comparisons
|
Baseline Comparisons |
|||||
|
Model |
NFI |
RFI |
IFI |
TLI |
CFI |
|
Delta1 |
rho1 |
Delta2 |
rho2 |
||
|
Default model |
0,989 |
0,983 |
0,986 |
0,964 |
0,984 |
|
Saturated model |
1 |
1 |
1 |
||
|
Independence model |
0 |
0 |
0 |
0 |
0 |
v NFI
NFI = Normed fit Index also called Delta 1 (Bollen, 1898b), which consists of scaling values between the (terribly fitting) independence model and the (perfectly fitting) saturated model.
|
Interpretation:
|
|
|
A value of NFI = 1 indicates a perfect fit. |
|
|
While models with a value NFI < 0,9 can usually be significantly improved |
Bentler & Bonett, 1980 |
|
A value NFI ≥ 0,9 indicates a reasonable fit |
Bentler & Bonett, 1980 |
|
Suggested that values above 0.95 indicate a good fit, values between 0.90 and 0.95 indicate an acceptable fit, and values below 0.90 indicate a poor fit. |
Hu and Bentler 1999 |
|
|
www.StatistischeBeratung.de |
NFI are 0,989 for our tested (default) model, this is considered an excellent fit.
v RFI
RFI = Relative fit Index and derived from NFI. The reference values for RFI (Relative fit Index) are not as established as for other fit indices.
The reference values may depend on the complexity of the model and the sample size.
|
Interpretation:
|
|
|
A value of RFI = 1 indicates a perfect fit. |
|
|
A value of RFI closed to 1 indicate a very good fit |
|
|
A value RFI ≥ 0,9 indicates a reasonable fit |
|
|
suggest that values above 0.90 indicate an acceptable fit, and values above 0.95 indicate a good fit |
Hu and Bentler, 1999 |
|
recommends a cutoff of 0.90 for acceptable fit, but notes that the reference values may depend on the complexity of the model and the sample size. |
Kline, 2011 |
|
|
www.StatistischeBeratung.de |
RFI are 0,983 for our tested (default) model, this is considered an excellent fit.
v IFI
IFI = Incremental fit Index.
|
Interpretation:
|
|
|
A value of IFI = 1 indicates a perfect fit. |
|
|
A value of IFI closed to 1 indicate a very good fit |
|
|
A value IFI ≥ 0,9 indicates a reasonable fit |
|
|
Suggest that IFI values of 0,90 or higher indicate good model fit, while values between 0,80 and 0,90 suggest acceptable fit |
Bentler, 1990; Hu & Bentler, 1999 |
|
Suggested more conservative cutoffs, such as IFI values of 0,95 or higher for good fit |
Marsh, Hau, & Wen, 2004 |
|
|
www.StatistischeBeratung.de |
It's important to note that reference values for IFI can vary depending on the complexity and size of the model, as well as the sample size and characteristics of the population being studied. Therefore, researchers should interpret IFI values in the context of their specific analysis and use their judgment to determine what constitutes acceptable or good fit.
IFI are 0,986 for our tested (default) model, this is considered an excellent fit.
v TLI *
TLI = Tucker-Lewis coefficient also known as Bentler-Bonett non-normed fit index (NNFI) ranges from (but not limited to) 0 to 1 where a value closer to 1 represents a very good fit while 1 represents a perfect fit.
The reference values for TLI (Tucker-Lewis Index) vary depending on the sample size and complexity of the model.
|
Interpretation:
|
|
|
A value of TLI = 1 indicates a perfect fit. |
|
|
Some researchers have suggested that TLI values above 0,80 are acceptable in smaller samples or less complex models. |
|
|
For the model to be acceptable it should have a TLI value higher than 0,9 |
Brown, 2006 |
|
For an excellent model it is necessary that the TLI value be higher than 0,95 |
Brown, 2006 |
|
A value TLI ≥ 0,9 indicates a reasonable fit |
|
|
|
www.StatistischeBeratung.de |
TLI are 0,964 for our tested (default) model, this is considered an excellent fit.
v CFI *
CFI = Comparative fit Index has value truncated between 0 and 1.
|
Interpretation:
|
|
|
A value of CFI = 1 indicates a perfect fit. |
Hu & Bentler, 1999 |
|
A values of CFI closed to 1 show a very good fit. |
|
|
A CFI value of ≥ 0,95 |
Hu & Bentler, 1999 |
|
A CFI value of ≥ 0,90 |
Homburg/Baumgartner, 1998, S.363 |
|
A value CFI ≥ 0,90 indicates an acceptable fit |
Fan et al., 1999 |
|
A CFI value of ≥ 0,95 is considered an excellent fit for the model |
West et al., 2012 |
|
|
www.StatistischeBeratung.de |
CFI are 0,984 for our tested (default) model, this is considered an excellent fit.
| Cite this article in your research paper: |
| APA Statistische Beratung Leonardo Miljko (datum) How to interpret SEM model fit results in AMOS. Retrieved from https://www.StatistischeDatenAnalyse.de/images/services/How_to_interpret_SEM_model_fit_results_in_AMOS.pdf . |
|
Harvard
Statistische Beratung Leonardo Miljko January 10, 2020 How to interpret SEM model fit results in AMOS. viewed datum < https://www.StatistischeDatenAnalyse.de/images/services/How_to_interpret_SEM_model_fit_results_in_AMOS.pdf > |
Wichtiger Hinweis: Der Originalinhalt ist auf Kroatisch. Die Übersetzung ins Deutsche und Englische erfolgte über einen Web-Übersetzer. Wir entschuldigen uns für die Fehler.
