Skip to main content
. 2006 Apr;15(2):83–89. doi: 10.1136/tc.2003.007237

Table 4 Results of the structural equation modelling using full information maximum likelihood for six countries: path‐coefficients (with standard errors), significance levels and effect sizes (ES) for path 4, 5, 6 and 7.

Finland Denmark Netherlands United Kingdom Spain Portugal
n = 1243 n = 572 n = 1987 n = 1746 n = 647 n = 907
Friend–adolescent(path 4) 0.002 0.032 −0.184 −0.205 0.241 0.859
(0.148) (0.179) (0.087) (0.166) (0.126) (0.308)
NS NS p = 0.0344 NS NS p = 0.005
ES = 0.00% ES = 0.005% ES = 0.28% ES = 0.13% ES = 0.77% ES = 1.16%
Adolescent–friend(path 5) 0.133 0.333 0.243 0.224 0.163 0.040
(0.035) (0.060) (0.033) (0.040) (0.066) (0.075)
p<0.001 p<0.001 p<0.001 p<0.001 p = 0.013 NS
ES = 1.63% ES = 5.91% ES = 4.57% ES = 3.72 % ES = 1.60% ES = 0.05%
Parent–adolescent(path 6) 0.328 0.351 0.156 0.141 0.024 0.122
(0.092) (0.150) (0.054) (0.048) (0.113) (0.086)
p<0.001 p = 0.0195 p = 0.004 p = 0.004 NS NS
ES = 1.55% ES = 0.96% ES = 0.57% ES = 0.79% ES = 0.01% ES = 0.23%
Parent–friend(path 7) 0.148 0.248 0.130 0.068 0.108 0.045
(0.05) (0.107) (0.037) (0.027) (0.093) (0.062)
p = 0.003 p<0.001 p<0.001 p = 0.012 NS NS
ES = 1.18% ES = 1.21% ES = 1.27% ES = 0.89% ES = 0.41% ES = 0.11%