NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
From: Greg Rudzinski
Date: 2013 Jan 4, 21:00 -0800
Here are 20 index error observations of Procyon using a Tamaya Jupiter with 7 x 35mm scope.
0.2' 0.7'
0.4' 0.7'
0.4' 0.6'
0.6' 0.4'
0.8' 0.6'
0.6' 0.7'
0.7' 0.7'
0.7' 0.4'
0.7' 0.7'
0.5' 0.4'
n=20
_
x = 0.575'
Sx = 0.1585'
All observations are off the arc.
Greg Rudzinski
[NavList] Re: Standard Deviation Question
From: Bill Morris
Date: 4 Jan 2013 19:30
"...when should I be using stdDevPop and when should I be using stdDevSamp?"
Not being a maths whiz either (nor a statistician)I would say that for small numbers you should use stdDecSamp. As a rule of thumb, I have always regarded a sample of less than 30 as being "small". As you have seen, using the stdDevPop function gives you a larger figure for the standard deviation.
The difference is unimportant in large samples. For example in 60 estimations of index error , the SD pop was 0.228 and the SD sample was 0.226.
I am inlcined to doubt the value of giving SDs for samples of n = 5. A sample size of n = 10 seems to be marginal; 20 would be more better. May we have a statistician's ruling?
Bill Morris
Pukenui
New Zealand
----------------------------------------------------------------
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
----------------------------------------------------------------