In case of non-compliance
of the assumption about the normality, the non-parametric equivalent of the variance
analysis with repeated measurements – Friedman’s test– was used to the analysis
of comparisons of mean results over time. However, in case of non-compliance
of the assumption of sphericity, the multidimensional approach and the multidimensional
variance analysis (MANOVA) were used. Additionally, in case of receiving
significant results the analysis of multiple comparisons in pairs (post-hoc tests) was
conducted in order to accurately determine which two averages are significantly different
from each other. Moreover, in case of significant results, the ɛ2 coefficient, which is
the estimator of the variance of the dependent variable (results of the applied questionnaires)
explained by the independent variable (intervention – group psychoeducation)
in the sample was calculated.