Table 2.
Model fit indices for SEM of COVID-19 preventive behaviors.
| SEM model | χ2 | CFI | RMSEA | 90% confidence interval | SRMR | AIC | BIC | |||
|---|---|---|---|---|---|---|---|---|---|---|
| χ2 | (df) | p | Lower bound | Upper bound | ||||||
| Model 1 | 0.01 | 1 | =0.912 | 1.00 | 0.000 | 0.001 | 0.021 | 0.001 | 31816.16 | 31892.41 |
| Model 2 | 0.04 | 1 | =0.850 | 1.00 | 0.000 | 0.000 | 0.029 | 0.001 | 31629.33 | 31822.90 |
***p < 0.001. CFI, comparative fit index (CFI ≥ 0.90 is acceptable, ≥0.95 is good); RMSEA, root mean square error of approximation (RMSEA ≤ 0.08 recommended); SRMR, standardized root mean residual (SRMR ≤ 0.08 recommended); AIC, Akaike's information criterion; BIC, Bayes information criterion (BIC) (lower values indicate a better fit, therefore the model with the lowest AIC and BIC is the best fitting model). Model 1, the baseline model which contained first five variables presented in Table 1 and all possible links between them (without a link between conspiracy beliefs and fear due to too low correlation coefficient between these two variables). Model 2, a more complicated version of Model 1 with the socio-demographic variables added as covariates.