Detecting the significance of the differences using the Friedman test and post hoc comparisons of the mean ranks of the related samples with the old and new versions of SPSS
Most experimental research uses a single-group or two-group design with repeated measurements. However, it uses the Wilcoxon test to detect the significance of differences between the mean ranks of two paired samples as pairs of individual measurements without checking the assumptions that must be met before using this test because you are making multiple comparisons, which Increases the likelihood of announcing a significant result when you shouldn't (Type I error). The Friedman Test is a nonparametric alternative to one-way analysis of variance (ANOVA) with repeated measures. It is used to test differences between groups when the dependent variable being measured is ordinal. It can also be used for continuous data that does not meet the assumptions necessary to perform a one-way analysis of variance (ANOVA) for repeated measures (for example, data that have identified deviations from normality – i.e. normality of the distribution). Hence, this article discusses the Friedman Test, the assumptions on which it is based, and procedures for using it when there is no need or need to conduct multiple comparisons between pairs of paired groups. Providing a Bonferroni Adjustment in the case of using the Wilcoxon test to compare pairs of paired samples in the case of significance of the Friedman test statistic, in addition to revealing the significance of the differences between the paired samples using SPSS program procedures for versions from version 18 until the latest version.