Welcome to the MapMan Family of Software Forum

Please do not hesitate to register and post your question.

Don't forget to subscribe to your posted message so you get notified on updates.
Every question you post will help others and or enhance the software!

Post a question,   post a bug!

Welcome to the MapMen Family of Software Forum Welcome to the MapMen Family of Software Forum

Using MapMan

overrepresented and underrepresented bins

Hi,

I would like to know if the Wilcoxon test implemented in Mapman is comparable to the Fisher's test to search for overrepresented categories.
Since the Wilcoxon test search for a different behavior, the bins with a good p-value selected with the wilcoxon test can be considered only overrepresented or maybe underrepresented too?

Thank you.

Laura

RE: overrepresented and underrepresented bins
Answer
8/28/10 7:45 AM as a reply to Laura Miozzi.
Dear Laura,

The Wilcoxon test is not compareable to the Fisher test, even though the results often are :-) For the FIsher overrepresentation test you have to set a threshold e.g. p<0.05 Abs ( log fold change) >=1, then you coun't the genes per bin that are changed to assess significance.

In the case of the Wilcoxon Test you look at all the genes in a bin and compare their log fold changes against all genes not in that bin. (It is based on ranks, so a non-parametric test)

Now often you see some very significant genes in a bin but also a consistent drift towards up- or downregulation...

Best Wishes,
Björn

RE: overrepresented and underrepresented bins
Answer
2/27/24 4:13 AM as a reply to Laura Miozzi.
The comparison between the Wilcoxon test and Fisher's test in Mapman for searching overrepresented categories is like an IQ test for statistical analysis!