Absolute values or Log-transformed data

#1
I want to perform a non parametric test (mann-whitney) for my experiments that is briefly quantification of viral load (Real Time Polymerase chain reaction). My final result is the amount of RNA copies per microliter (i.e. 1e10 copies per microliter). I log transform these values in order to better represent the data (graphically). My question is: for the statistic matters, should I run the statistical test with the log-transformed data or with the raw data?

Thank you everyone!

Best

Julian
 

hlsmith

Omega Contributor
#2
If you are using a non-parametric you probably don't need to log transform them. You may come into issues if later on you try to publish multiple formatting of the same data, it could confuse readers.


Are you planning on submitting mixed formatted results? I think you also need to keep in mind if you used a mono rank transformation, can't remember is that is the real name for it or not. But moreover, do values stay in the same rank order when transforming them.