Timer accuracy and abstruse statistical arguments

["John J. Stimson-III" <john@harlie.idsfa.net>]

On Wed, Jun 02, 2004 at 07:11:20AM -0700, Stephen Bowlus wrote:
> This argument is independent of the source of the variation (lights, 
> clock, lead foot, warm tires, butterflies in South America).

Actually, it assumes that the source of variation is random and the
variation looks like a bell curve.  If there is something that can
happen during the run that causes a large shift in the time, but it
only happens sometimes, then it doesn't follow your rules.  In
statistics, the result is called a "bi-modal distribution."

-- 

john@idsfa.net                                              John Stimson
http://www.idsfa.net/~john/                              HMC Physics '94