Table 1.
Confirmatory factor analyses (CFA) and tests of invariance on the Compulsive Sexual Behavior Disorder Scale (CSBD-19)
| Model | WLSMV χ2 (df) | CFI | TLI | RMSEA | 90% CI | Comparison | Δχ2 (df) | ΔCFI | ΔTLI | ΔRMSEA | |
| 5-factor first-order CFA (Sample 1) | 7148.851∗(142) | 0.944 | 0.932 | 0.079 | 0.077–0.080 | — | — | — | — | — | |
| 5-factor first-order CFA (Sample 2) | 327.290∗(142) | 0.983 | 0.980 | 0.053 | 0.045–0.060 | — | — | — | — | — | |
| 5-factor first-order CFA (Sample 3) | 249.477∗(142) | 0.994 | 0.993 | 0.040 | 0.032–0.048 | — | — | — | — | — | |
| 5-factor first-order CFA (Sample 4) | 286.037∗(142) | 0.967 | 0.960 | 0.052 | 0.043–0.060 | — | — | — | — | — | |
| Language invariance (Sample 1, Sample 2, Sample 3, Sample 4) | |||||||||||
| M1. Configural | 7847.926∗(568) | 0.948 | 0.937 | 0.074 | 0.073–0.076 | – | – | – | – | – | |
| M2. Metric | 7929.214∗(610) | 0.948 | 0.941 | 0.072 | 0.070–0.073 | M2-M1 | 204.068∗(42) | 0.000 | +0.004 | −0.002 | |
| M3. Scalar | 7146.882∗(709) | 0.954 | 0.956 | 0.062 | 0.061–0.064 | M3-M2 | 283.851∗(99) | +0.006 | +0.015 | −0.010 | |
| M4. Residual | 6104.670∗(766) | 0.962 | 0.966 | 0.055 | 0.053–0.056 | M4-M3 | 293.405∗(57) | +0.008 | +0.010 | −0.007 | |
| M5. Latent variance-covariance | 3956.990∗(811) | 0.978 | 0.981 | 0.041 | 0.040–0.042 | M5-M4 | 372.456∗(45) | +0.016 | +0.015 | −0.014 | |
| M6. Latent means | 3963.853∗(826) | 0.978 | 0.981 | 0.040 | 0.039–0.042 | M6-M5 | 111.208∗(15) | 0.000 | 0.000 | −0.001 | |
| Gender invariance (Merged sample) | |||||||||||
| Baseline men | 4806.565∗(142) | 0.953 | 0.943 | 0.075 | 0.074–0.077 | – | – | – | – | – | |
| Baseline women | 2768.242∗(142) | 0.938 | 0.925 | 0.073 | 0.070–0.075 | – | – | –` | – | – | |
| M1. Configural | 7406.038∗(284) | 0.949 | 0.938 | 0.073 | 0.072–0.075 | – | – | – | – | – | |
| M2. Metric | 7603.677∗(298) | 0.948 | 0.940 | 0.073 | 0.071–0.074 | M2-M1 | 251.151∗(14) | −0.001 | +0.002 | 0.000 | |
| M3. Scalar | 7236.398∗(331) | 0.950 | 0.949 | 0.067 | 0.066–0.068 | M3-M2 | 240.306∗(33) | +0.002 | +0.009 | −0.006 | |
| M4. Residual | 6625.373∗(350) | 0.955 | 0.956 | 0.062 | 0.061–0.063 | M4-M3 | 217.549∗(19) | +0.005 | +0.007 | −0.005 | |
| M5. Latent variance-covariance | 3111.513∗(365) | 0.980 | 0.982 | 0.040 | 0.039–0.042 | M5-M4 | 93.417∗(15) | +0.025 | +0.026 | −0.022 | |
| M6. Latent means | 5016.435∗(370) | 0.967 | 0.969 | 0.052 | 0.051–0.053 | M6-M5 | 839.223∗(5) | −0.013 | −0.013 | +0.012 | |
Note. WLSMV = weighted least squares mean- and variance-adjusted estimator; χ2 = Chi-square; df = degrees of freedom; CFI = comparative fit index; TLI = Tucker-Lewis Index; RMSEA = root-mean-square error of approximation; 90% CI = 90% confidence interval of the RMSEA; ΔCFI = change in CFI value compared to the preceding model; ΔTLI = change in the TLI value compared to the preceding model; ΔRMSEA = change in the RMSEA value compared to the preceding model. Bold letters indicate the final levels of invariance that were achieved. In the language-based comparison, the highest level of measurement invariance (i.e., latent mean invariance) was achieved, indicating that the CSBD-19 functions the same way in each examined language version. In the gender-based comparison, latent variance-covariance was achieved, but latent means invariance was not, indicating important latent mean differences between men and women.∗P < 0.001