Table 4. Fit Indices and Comparisons of ESEM Invariance Models (32-countries group and country clusters).
| Model | SB- χ2 [df] | CFI | TLI | RMSEA | CI90-RMSEA | SRMR | ΔCFI | ΔTLI | ΔRMSEA | ΔSRMR |
|---|---|---|---|---|---|---|---|---|---|---|
| Total TALIS 2013 Sample | ||||||||||
| Configural invariance | 9,489.4 [1,056]* | .979 | .958 | .039 | [.039, .040] | .018 | – | – | – | – |
| Metric invariance | 15,288.1 [1,893]* | .967 | .963 | .037 | [.037, .038] | .041 | –.012 | +.005 | –.002 | +.023 |
| Scalar invariance | 43,780.5 [2,172]* | .896 | .899 | .061 | [.061, .062] | .071 | –.071 | –.064 | +.024 | +.030 |
| Strict invariance | 60,441.1 [2,544]* | .855 | .880 | .066 | [.066, .067] | .121 | –.041 | –.019 | +.005 | +.050 |
| East and South-East Asian countries (Japan, Korea, Malaysia, Singapore) | ||||||||||
| Configural invariance | 1,719.3 [132]* | .981 | .961 | .050 | [.048, .052] | .016 | – | – | – | – |
| Metric invariance | 2,614.5 [213]* | .971 | .964 | .048 | [.046, .050] | .036 | –.010 | +.003 | –.002 | +.020 |
| Partial scalar invariance | 3,489.4 [231]* | .960 | .955 | .054 | [.052, .055] | .042 | –.011 | –.009 | +.006 | +.020 |
| Scalar invariance | 5,579.1 [240]* | .935 | .929 | .067 | [.066, .069] | .052 | –.025 | –.016 | +.006 | +.010 |
| Strict invariance | 6,679.8 [276]* | .922 | .925 | .069 | [.067, .070] | .077 | –.013 | –.004 | +.002 | +.025 |
| Anglo-Saxon countries (Australia, England, Unites States of America) | ||||||||||
| Configural invariance | 954.6 [99]* | .972 | .945 | .050 | [.047, .053] | .020 | – | – | – | – |
| Metric invariance | 1,052.0 [153]* | .971 | .963 | .041 | [.039, .043] | .026 | –.001 | +.018 | –.009 | +.006 |
| Partial scalar invariance | 1,143.0 [165]* | .969 | .962 | .041 | [.039, .043] | .029 | –.002 | –.001 | –.009 | +.006 |
| Scalar invariance | 1,261.6 [171]* | .965 | .959 | .043 | [.041, .045] | .032 | –.004 | –.003 | +.002 | +.003 |
| Strict invariance | 1,291.5 [195]* | .965 | .964 | .040 | [.038, .042] | .040 | .000 | +.005 | –.003 | +.008 |
| Nordic countries (Denmark, Finland, Norway, Sweden) | ||||||||||
| Configural invariance | 1,434.4 [132]* | .980 | .960 | .038 | [.037, .040] | .018 | – | – | – | – |
| Metric invariance | 2,016.3 [213]* | .973 | .966 | .036 | [.034, .037] | .033 | –.007 | +.006 | –.002 | +.015 |
| Partial scalar invariance | 3,209.4 [231]* | .955 | .948 | .044 | [.043, .045] | .039 | –.018 | –.018 | +.008 | +.006 |
| Scalar invariance | 5,307.7 [240]* | .923 | .915 | .056 | [.055, .057] | .056 | –.022 | –.033 | +.012 | +.017 |
| Strict invariance | 6,429.5 [276]* | .907 | .911 | .058 | [.056, .059] | .082 | –.016 | –.004 | +.002 | +.026 |
Note. SB- χ2 = Satorra-Bentler corrected χ2 value. CI90-RMSEA = 90% confidence interval of the RMSEA.
* p < .01. For the total TALIS 2013 sample, partial scalar was not tested due to a large number of possible combinations that could be used to constrain some of the item intercepts across the 32 participating countries.