> >Using either n or (n-1) in the denominator gives a BIASED estimate of the >standard deviation. >Using sumsq/(n-1) gives an unbiased estimate of the variance. >Using sqrt( sumsq/(n-1.5) ) gives an estimate of the standard deviation >which is almost unbiased.
but ... as n goes up ... this becomes a trivial bias ... right? the reason we even worry about and take the n minus something into account is, that with small samples ... sample estimates can be considerably off ... if you have an SRS (or better than SRS) samples of n=500 or n=1500 ... we are just whistling dixie about the potential problems here . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
