Hi there,
I have a non-normal distributed continuous variable (gene expression) for which I want to know whether it is associated to:
- the classification group (Group A and Group B, unrelated categorical variable)
- time (0, 1h, 24h) (related categorical variable).
I have data for 6 individuals in each group, for each time-point.
Could you help me to find the best statistical approach? How can I apply it using SPSS?
Thanks for your help! :-)
Teresa
This is more complicated than it might first appear. The best reference is Prof. Marie Davidian's course notes. Start with the material on repeated measures and move forward as needed. The link is below. Best wishes, David Booth BTW SPSS is probably not the software of choice for this.
https://www.stat.ncsu.edu/people/davidian/courses/st790/notes.html
You could perform non parametric tests In Spss. analysis-non parametric tests- 2 independent samples of k independent samples. Those are Mann Whitney u and Kruskall-Wallis h
Hello
1. Since the normality assumption is violated, the non-parametric tests could be developed.
2. Strictly speaking, non-parametric statistics do not test for differences in means. They cannot, since, for example, they use scores turned into ranks. Usually they test whether the ranks in one group are typically larger or smaller than the ranks in the other groups.
3.We have included the sign test and Wilcoxon’s test for related data. In other words, they are the non-parametric equivalents to the related t-test. The Wilcoxon test should be used in preference to the sign test when comparing score data.
4.The Mann–Whitney U-test is used for unrelated data. That is, it is the non-parametric equivalent to the unrelated t-test.
Regards,
Zuhair
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS