Spss 26.0 statistics

Statistical analyses were performed using the IBM SPSS 26.0 Statistics program. The normal distribution of all relevant variables was tested using the Kolmogorov–Smirnov test. The significant results (p > 0.05) indicate that the distributions are normal. The results of the skewness test, the kurtosis test, and the p-p graphs allowed us to decide that the variable could be considered as normally distributed. The results (absolute values below 1.96 for skewness and kurtosis in the z-transformed variables) were considered normally distributed when checking for anomalies in the p-p plots [17 (link)]. All z-transformed total scores met the stated criteria and were, therefore, treated as normally distributed. The means are considered significantly different when the p-value is less than 0.05 (the same applies to the p-value of the chi-squared). Following the confirmation of the normality test, we conducted two basic regression linear regression analyses to examine the relationship between the degree of traumatic exposure and the children’s levels of attachment to their parents, on the one hand, and their levels of attachment to their peers, on the other hand.

Data were analysed using IBM SPSS 26.0 Statistics and expressed as mean values ± SD. Data from different groups were compared using one‐way ANOVA followed by Fisher's least significant difference comparison. Data from clinical retrospective study were used paired‐sample t‐test. A p‐value <0.05 was considered to indicate a significant difference, and p‐value <0.01 considered to indicate a very significant difference.

Statistical analyses were performed in GraphPad Prism version 7.0a (GraphPad Software), SPSS 26.0 Statistics and EXCEL. Data were analysed for statistical significance using one-way analysis of variance (ANOVA) along with Fisher’s least significant difference test (Figs. 1d, 4c and Supplementary Fig. 2a), one-way ANOVA followed by Šidák’s multiple-comparison test (Fig. 3b, d) and unpaired two-tailed Student’s t test in other experiments. Error bars indicate the standard deviation (SD), and the data sets are represented as the mean ± SD. Significance values are indicated as follows: *P < 0.05, **P < 0.01 and ***P < 0.001.