Table 3. Goodness of fit indices for every pair of nested models and chi-square statistics for comparing the models.
| Model | DF | χ2 | χ2 / DF | RMSEA | SRMR | CFI | GFI | NFI | IFI | (Δχ2, DF) † |
|---|---|---|---|---|---|---|---|---|---|---|
| Unconstrained | 229 | 981.65 | 4.20 | 0.024 | 0.029 | 0.94 | 0.98 | 0.93 | 0.94 | Assuming to be correct |
| Measurement weights | 243 | 1021.42 | 4.28 | 0.024 | 0.030 | 0.93 | 0.98 | 0.92 | 0.94 | 39.77*, DF = 14 |
| Structural weights | 284 | 1414.91 | 4.98 | 0.027 | 0.040 | 0.91 | 0.97 | 0.90 | 0.87 | 433.26*, DF = 55 |
| Structural residuals | 299 | 2331.61 | 7.80 | 0.035 | 0.047 | 0.85 | 0.96 | 0.83 | 0.78 | 1349.96*, DF = 70 |
| Measurement residuals | 346 | 300.62 | 8.67 | 0.075 | 0.046 | 0.80 | 0.93 | 0.78 | 0.76 | 2019.97*, DF = 117 |
† Chi-square test is used to test the null hypothesis that the more constrained model is correct under the assumption that the less constrained model is correct. The model with all parameters differed in two genders was significantly better than others which had some constraints on the parameters.
* P < 0.001
χ2: Chi-Square value, DF: Degrees of Freedom, RMSEA: Root Mean Square Error of Approximation, SRMR: Standardized Root Mean Square Residual, NFI: Normed Fit Index, CFI: Comparative Fit Index, IFI: Incremental Fit Index, GFI: Goodness of Fit Index.