I'm helping out a Education Master student with her Thesis. She has conducted a questionnaire in which she, among other things, asked two 5-point Likert scale questions: One about the rate of familiarity with the term "graphic novels", the second question about the familiarity with the concept "graphic novels". The data is not normally distributed, so a one sample T-test is not appropriate, but what can I do in this situation?
as the variable is measured on ordinal scale, non-parametric test is most appropriate test.
in non-parametric test, we do not test the difference between the means of two tests. Rather, we test the difference in orderings of the observations(if the variable is measured in ordernal scale), difference in ranks or difference in signs etc.,
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS