Table 2.
Comparison of different models of the Czech DS-R using a confirmatory factor analysis.
| χ2 | df | RMSEA | RMSEA 90%CI | CFI | TLI | |
|---|---|---|---|---|---|---|
| Both samples | ||||||
| 1-factor model | 870** | 275 | 0.063 | 0.058–0.068 | 0.746 | 0.723 |
| 3-factor model | 696** | 272 | 0.053 | 0.048–0.058 | 0.819 | 0.800 |
| Bifactor model | 530** | 250 | 0.045 | 0.040–0.050 | 0.966 | 0.959 |
| Sample 1 | ||||||
| 1-factor model | 480** | 275 | 0.061 | 0.052–0.070 | 0.688 | 0.660 |
| 3-factor model | 443** | 272 | 0.056 | 0.046–0.065 | 0.074 | 0.713 |
| Sample 2 | ||||||
| 1-factor model | 723** | 275 | 0.068 | 0.062–0.074 | 0.743 | 0.720 |
| 3-factor model | 579** | 272 | 0.057 | 0.050–0.063 | 0.824 | 0.806 |
**χ2 test is significant at p < 0.001, df degrees of freedom, RMSEA root mean square error of approximation, CFI comparative fit index, TLI Tucker-Lewis index; bifactor model after removing the loading of items 3 and 18 on the subscales.