Re: simple maths question

[aah@nofs.navy.mil]

john wrote:
>If I take the mean of forty odd V measures from one night is the
>standard deviation the standard deviation calculated upon those measures
>or the mean of the standard deviations given for those measures???
  It depends on what you are measuring/reporting.  The first is
the standard deviation of a single measure; how far any given datapoint
is likely to be from the true value.  The second is not normally used,
but something similar is the standard deviation of the mean,
which is the standard deviation of a single measure divided by the
square root of the number of observations.  You use this latter
error when reporting the average value, such as the average of the
40 measures you mentioned.  It tells how far that average is likely
to be from the true value.
  Just about any statistics book will discuss populations and standard
deviations; the one I got in graduate school was Bevington, Data Reduction
and Error Analysis for the Physical Sciences, which is still in print if
I recall correctly.  Or, look at Henden/Kaitchuck.
Arne