Citation needed for removing 3 Stdev outliers

#1
Hi,
In a research paper, I had remove values that were 3 standard deviations away from the mean. The values simply didn't make any sense.
I have been searching all over for a citation supporting the 3 standard deviation rule but haven't found much as most researchers don't seem to include one... but I do need one.

Does anyone know of one?
 

noetsi

Fortran must die
#2
You won't find any such rule in all liklihood. The conventional wisdom (given that statisticians always disagree on everything):p is that there is no specific level at which you can automatically remove outliers. Generally, you need to try to explain why the outliers are occuring (if they are not simply a mistake in data collection). Commonly extreme outliers reflect model mispecification, multiple populations etc. Three standard deviations is a useful tool to identify extreme outliers, but you use it to explain why they occur rather than removing them.

I spent a fair time reading various material on outliers. It is common to see warnings about automatically removing them.