Table 5.
Fit indices for measurement invariance.
| Model | WLSMVχ2 | df | Δχ2 | Δdf | TLI | CFI | ΔTLI | ΔCFI | RMSEA (90% CI) |
|---|---|---|---|---|---|---|---|---|---|
| Bi-factor boys | 447.379∗ | 117 | – | – | 0.982 | 0.986 | – | – | 0.057 (0.052, 0.063) |
| Bi-factor girls | 573.146∗ | 117 | – | – | 0.982 | 0.986 | – | – | 0.051 (0.047, 0.056) |
| A-Metric invariance | 956.841∗ | 266 | – | – | 0.986 | 0.988 | – | – | 0.047 (0.044, 0.050) |
| B-Scalar invariance | 846.772∗ | 320 | 108.271 | +54 | 0.991 | 0.991 | +0.005 | +.003 | 0.038 (0.034, 0.041) |
WLSMV, weighted least squares with mean and variance adjustment; df, degrees of freedom; TLI, Tucker-Lewis Index; CFI, comparative fit index; RMSEA, root-mean-square error of approximation; Δχ2, change in χ2 relative to the preceding model; Δdf, change in degrees of freedom relative to the preceding model; ΔCFI, change in comparative fit index relative to the preceding model; ΔTLI, change in Tucker-Lewis Index relative to the preceding model. ∗p < 0.05. Chi-square difference test with WLSMV estimation is different from the conventional chi-square difference test.