home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: sci.math.stat
- Path: sparky!uunet!munnari.oz.au!metro!sunb!laurel.ocs.mq.edu.au!wskelly
- From: wskelly@laurel.ocs.mq.edu.au (William Skelly)
- Subject: Re: Standard Deviation.
- Message-ID: <1992Aug16.211142.27499@mailhost.ocs.mq.edu.au>
- Keywords: (n) versus (n-1)
- Sender: news@mailhost.ocs.mq.edu.au (Macquarie University News)
- Nntp-Posting-Host: laurel.ocs.mq.edu.au
- Organization: Macquarie University, Australia.
- References: <1992Aug14.172833.11844@cbfsb.cb.att.com>
- Date: Sun, 16 Aug 1992 21:11:42 GMT
- Lines: 21
-
- In article <1992Aug14.172833.11844@cbfsb.cb.att.com> rizzo@cbnewsf.cb.att.com (anthony.r.rizzo) writes:
- >Can someone explain why calculating the Standard Deviation (SD),
- >for small samples, with (n-1) in the denominator is better than
- >doing so with (n) in the denominator? I'm sure that there's
- >a perfectly good reason for doing so. But we, lowly engineers
- >aren't usually told the reason. Thanks now, for your response later.;-)
- >
- >Tony Rizzo (att.com!homxc!rizzo)
- >
-
- Well the (n-1) term is used when you have a "biased" condition.
- I don't know the full theoretical reasons, but if you use "n"
- instead of (n-1) your standard deviation is _smaller_. so if you
- are less than sure that your sample is truely representative of
- your population you use "n-1" which provides for a slightly
- larger standard deviation. Of course when you are dealing with
- very small samples (n < 30 maybe) this could make a heck of a
- difference in the resulting std. dev. value.
-
- chris
-
-