In scientific literature, effect sizes are reported using parametric tests such as cohn's d (most of the time). I am interest in equivalent non-parametric tests. Suggestions are highly appreciated.
I found what could be helpful answer to your question in the following link:
https://www.graphpad.com/guides/prism/7/statistics/stat_sample_size_for_nonparametric_.htm?toc=0&printWindow
Depending on the nature of the distribution, the nonparametric tests might require either more or fewer subjects. But they never require more than 15% additional subjects if the following two assumptions are true:
•You are looking at reasonably high numbers of subjects (how high depends on the nature of the distribution and test, but figure at least a few dozen)
•The distribution of values is not really unusual (doesn't have infinite tails, in which case its standard deviation would be infinitely large).
So a general rule of thumb is this (1):
If you plan to use a nonparametric test, compute the sample size required for a parametric test and add 15%.
You can calculate effect size for both parametric and Non-parametric test by using a software named G*power 3.1.9.2 which is free software also.
Just you require the parent distribution what you assumes(Normal,logistic,laplace or min ARE in this if you don't assume parent distribution then select min ARE), alpha , power and sample size.
I hope it helps.
Hi, can you please explain how to calculate the "effect size" with the Wilcoxon test for one sample?, with G*Power. Thank you
- Badges
- Science topic
- Similar topics
- Biological Science
- Physiology
- Physiological Processes
- Stress