Introduction

The Friedman test is one of the most important non-parametric statistical methods and is used as an alternative to the one-way repeated measures ANOVA. Its main purpose is to examine whether there are statistically significant differences between three or more measurements taken from the same group of participants under different conditions or at different time points. Its value lies in the fact that it does not require normally distributed data, unlike parametric tests, and therefore it can be applied in a wide range of research fields where data often deviate from the theoretical assumptions of parametric statistics. Examples of such applications can be found in psychology, education, and medical research, where the same participants are repeatedly evaluated in order to measure the effect of some intervention.

Assumptions of the Friedman Test

In order to use the Friedman test, specific assumptions related to the research design and the type of data must be met. The first assumption is that there must be only one group of participants, which is measured at three or more time points or experimental conditions. The Friedman test does not compare different groups but only the same group under repeated measurements. The second assumption concerns sampling, as it is necessary for the group to represent a random sample from the population in order for the results to be generalizable and to have external validity. The third assumption relates to the level of measurement of the dependent variable, which must be at least ordinal or continuous. This means that data from Likert scales, exam scores, weight measurements, intelligence levels, or any other variable expressed on a numeric scale or ranking can be used. Finally, the fourth assumption is perhaps the most characteristic one, as the samples are not required to follow a normal distribution. This feature differentiates the Friedman test from parametric ANOVA and makes it particularly useful in cases where normality is violated.

Procedure in SPSS

The application of the Friedman test in SPSS is straightforward, but requires attention from the researcher since the software does not automatically check whether the assumptions are met. The researcher must first organize the data in such a way that each row represents one participant and each column represents a different measurement or condition. Once the data entry is completed, the test is run through the Analyze menu, under Nonparametric Tests, specifically in Related Samples. There, the Friedman test is selected and the variables corresponding to the different measurements are included. After executing the procedure, SPSS provides the Friedman chi-square statistic and the corresponding p-value. The interpretation is based on this value, since if p is smaller than the predetermined level of significance, usually 0.05, then the null hypothesis is rejected and we conclude that there are statistically significant differences between the measurements.
In cases where the Friedman test indicates significance, further analyses are usually required to determine exactly where the differences lie. This is achieved with post-hoc tests such as the Wilcoxon signed-rank test, which compares pairs of measurements to highlight the specific conditions that differ from one another.

Conclusions

The Friedman test is a powerful tool for analyzing repeated measures when parametric methods cannot be used. Its flexibility in handling non-normal data and ordinal variables makes it particularly important in applied research contexts. SPSS provides a user-friendly environment for its implementation, but proper application and interpretation depend on an understanding of the assumptions and careful preparation of the data. Overall, the Friedman test enables researchers to reliably identify differences among multiple measurements of the same group and provides valid results even in cases where parametric statistics cannot be applied.