Table 3.
Multilevel linear model for life satisfaction score, ML estimates (se)
| Fixed effects | Model 1d | Model 2d | Model 3d | Model 4d | Model 5d |
|---|---|---|---|---|---|
| Transformed FASa | 0.86 (0.06) | 0.86 (0.06) | 0.86 (0.06) | −0.24 (0.34) | 3.99 (0.98) |
| Square of Transformed FASa | −0.66 (0.11) | −0.67 (0.11) | −0.67 (0.11) | −0.66 (0.11) | −0.66 (0.11) |
| Gini coefficientb | −0.09 (0.10) | −0.10 (0.10) | −0.08 (0.10) | ||
| GDP (PPP US$)c | 0.11 (0.09) | 0.10 (0.09) | 0.12 (0.09) | ||
| Transformed FAS*Ginib interaction | 0.34 (0.11) | ||||
| Transformed FAS*GDP (PPP US$)c interaction | −0.31 (0.10) | ||||
| Random effects parameters | |||||
| Level 1 (child) variance | 3.246 (0.020) | 3.246 (0.020) | 3.246 (0.020) | 3.246 (0.020) | 3.246 (0.020) |
| Level 2 (school) variance | 0.095 (0.007) | 0.095 (0.007) | 0.095 (0.007) | 0.095 (0.007) | 0.095 (0.007) |
| Level 3 (stratum) variance | 0.012 (0.004) | 0.012 (0.004) | 0.011 (0.004) | 0.012 (0.004) | 0.011 (0.004) |
| Level 4 (country) | |||||
| Variance (intercept) | 0.087 (0.023) | 0.083 (0.022) | 0.081 (0.021) | 0.079 (0.021) | 0.079 (0.021) |
| Variance (slope) | 0.108 (0.032) | 0.108 (0.032) | 0.108 (0.032) | 0.077 (0.025) | 0.078 (0.025) |
| Covariance (int,slope) | −0.026 (0.020) | −0.018 (0.019) | −0.015 (0.019) | −0.007 (0.016) | −0.007 (0.016) |
| −2logLikelihood | 235,913.7 | 235,913.1 | 235,912.5 | 235,902.9 | 235,903.1 |
| Number of parameters | 8 | 9 | 9 | 11 | 11 |
| AIC | 235,921.7 | 235,922.1 | 235,921.5 | 235,913.9 | 235,914.1 |
Via iterative generalized least squares (IGLS)
a FAS standardised using ridit transformation and centred
b Gini coefficient has been multiplied by 10 to make effect sizes equivalent to those of logged GDP (PPP US$)
c Log of GDP (PPP US$)
d Adjusting for sex, age and family structure