NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
From: David Fleming
Date: 2013 Jan 5, 20:15 -0800
To: wmh
As you say with 20 observations there is not much difference but strictly speaking you should use sample standard deviation.
Had more measurements of the index correction been made the average value would change, ie you do not know independent of the measurements what the average value for IC is; see Marcel's explanation.
Further the twenty measurements are just samples from the distrbution of potential measurements they are not the whole population of possible measurements.
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
----------------------------------------------------------------