Skip to main content
. 2018 May 15;9:169. doi: 10.3389/fpsyt.2018.00169

Table 4.

Model fitting results for each measurement invariance level of the RES across the English- and Dutch- speaking groups.

vs. χ2 df Δχ2 Δdf χ2/df CFI ΔCFI TLI RMSEA
1. Configural invariance: total sample 125.224 52 0.987 0.981 0.073
1a. Configural invariance: English language 68.352 26 0.987 0.981 0.085
1b. Configural invariance: Dutch language 57.336 26 0.986 0.981 0.064
2. Scalar invariance 1 197.990 75 75.614 23 3.29 0.977 −0.010 0.978 0.079
3. Partial scalar invariance 1 171.357 72 49.483 20 2.47 0.982 0.005 0.982 0.073

Model 1: multigroup two-factor model with free estimation of thresholds and factor loadings across groups. Model 1a and 1b: two-factor model with free estimation of thresholds and factor loadings for each language group. Model 2: multigroup two-factor model with thresholds and factor loadings constrained to be equal across groups. Model 3: multigroup two-factor model with thresholds and factor loadings constrained to be equal across groups, except for item 4. The model with the best model fitting indices is printed in bold, partial scalar invariance holds. vs. = versus (the model of comparison). χ2, df = chi-square test statistic value and degrees of freedom. Δχ2, Δdf = chi-square test statistic value and degrees of freedom for chi-square difference test between two nested models. χ2/df = ratio between χ2 and degrees of freedom for the chi-square difference test. ΔCFI = CFI difference between two nested models.