NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
From: David Fleming
Date: 2013 Jan 4, 18:21 -0800
At the risk of not understanding your question let me suggest an answer anyway.
sample standard deviation = square-root{n-1/n} X population standard deviation, where n is the number of data points you have.
Thus if you have many data points it doesn't matter particularlly which you use.
But when you have just a few points then the sample standard deviation is more appropriate as it shows you recognize that you don't actually know how the population of all potential measurements are distributed just how the ones you sampled are distributed.
Dave F.
----------------------------------------------------------------
NavList message boards and member settings: www.fer3.com/NavList
Members may optionally receive posts by email.
To cancel email delivery, send a message to NoMail[at]fer3.com
----------------------------------------------------------------