Model fit indices and model comparisons
| Model | D-separation criteria | Model fit | Comparison to model 1 | |||||
|---|---|---|---|---|---|---|---|---|
| χ2 | df | TLI | RMSEA | SRMR | Δχ2(df) | ΔTLI | ||
| 1. Partial mediation | met | 984.4 | 455 | 0.820 | 0.071 | 0.069 | ||
| 2. No mediation | not met | 1221.7 | 459 | 0.740 | 0.084 | 0.171 | 237.3(4) | 0.078 |
| 3. Full mediation | not met | 992.6 | 458 | 0.830 | 0.071 | 0.071 | 8.1(4) | 0.000 |
| 4. Full mediation with PCOV- > PE path added* | met | 985.1 | 458 | 0.820 | 0.070 | 0.070 | 0.6(3) | −0.002 |
| Model | D-separation criteria | Model fit | Comparison to model 1 | |||||
|---|---|---|---|---|---|---|---|---|
| df | TLI | RMSEA | SRMR | Δ | ΔTLI | |||
| 1. Partial mediation | met | 984.4 | 455 | 0.820 | 0.071 | 0.069 | ||
| 2. No mediation | not met | 1221.7 | 459 | 0.740 | 0.084 | 0.171 | 237.3(4) | 0.078 |
| 3. Full mediation | not met | 992.6 | 458 | 0.830 | 0.071 | 0.071 | 8.1(4) | 0.000 |
| 4. Full mediation with PCOV- > PE path added* | met | 985.1 | 458 | 0.820 | 0.070 | 0.070 | 0.6(3) | −0.002 |
Note(s): We used D-separation as a formal procedure for determining conditional independence based on the causal Bayesian network underlying the model to detect model misspecification. *We unrestricted the PCOV-- > PE path parameter to meet the D-separation criteria
Source(s): Authors’ own elaboration
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.