To determine the sample size necessary to assure appropriate statistical precision, the G*Power 3.1.9.4 program was used. The established effect size was 0.8, α error probability was 0.05 and power was 0.8. The non-central parameter δ was 2.88. The total sample size was 52 and actual power 0.807. The obtained results were statistically analyzed using MS Excel and Statistica 13.3 software (Statistica PL, StatSoft, Kraków, Poland). The normality of the distribution was checked using the Shapiro-Wilk test. The test results showed that the distributions of the examined values deviated from the normal distribution; therefore, in detailed statistical analyses, non-parametric tests were used. The results were presented as the middle value of the distribution—median, lower quartile value (Q25) and upper quartile value (Q75).
In order to demonstrate the significance of the differences, the non-parametric ANOVA Kruskal–Wallis rank test and the Mann–Whitney U test were used. The significance level was assumed at p < 0.05. To prove whether the observed correlations were statistically significant, the Spearman’s rank correlation coefficient significance test was used.
In order to demonstrate the significance of the differences, the non-parametric ANOVA Kruskal–Wallis rank test and the Mann–Whitney U test were used. The significance level was assumed at p < 0.05. To prove whether the observed correlations were statistically significant, the Spearman’s rank correlation coefficient significance test was used.