Table 5.
Mediation analysis for the average network
| β | % | Mediation model | ||||||
|---|---|---|---|---|---|---|---|---|
| X | Y | M | c | c′ | Attenuation | F(df) | Lower CI | Upper CI |
| PGRS | IQ | Mean edge weight | −0.474 | −0.253 | 46.62 | 8.20 (2, 43) | −0.657 | −0.048 |
| PGRS | IQ | Density | −0.527 | −0.168 | 62.76 | 4.63 (2, 43) | −0.431 | −0.002 |
| PGRS | IQ | Strength | −0.288 | −0.439 | −52.43 | 14.20 (2, 43) | −0.893 | −0.142 |
| PGRS | IQ | Global efficiency | −0.376 | −0.348 | 7.44 | 9.85 (2, 43) | −0.765 | −0.117 |
| PGRS | IQ | Clustering coefficient | −0.405 | −0.326 | 19.50 | 10.66 (2, 43) | −0.705 | −0.090 |
X: independent variable; Y: outcome variable; M: mediator; c: path from X to Y; c′: path from X to Y accounting for M.
Bold type face indicates significant mediation effect (confidence intervals do not include 0; Preacher and Hayes, 2008) and after FDR correction (P FDR < 0.05).
All tests of mediation are one‐tailed and bias‐corrected.