I was wondering if anyone could tell me why, when constructing a box-plot, it is always used that a value of:

Q1-1.5*IQR or lower, defines an outlier

Q1-3.0*IQR or lower, defines a far outlier.

the same with

Q3+1.5*IQR

Q3+3.0*IQR

where

Q1: left side of the box

Q3: right side of the box

IQR: Interquartile range

Is there any reason people uses 1.5 and 3.0? why not 2.0 and 4.0? where do those numbers come from, analytically?

Regards