Date:         Sat, 9 Dec 2006 17:54:54 -0500
Reply-To:     Statisticsdoc <statisticsdoc@cox.net>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Statisticsdoc <statisticsdoc@cox.net>
Subject:      Re: guessing mean of bounded variable with 1:30 sampling ratio
Comments: To: nicola.baldini2@unibo.it
In-Reply-To:  <7.0.0.16.2.20061201115818.021fb5e0@unibo.it>
Content-Type: text/plain; charset="us-ascii"

Nicola,

Richard raises an important point about random sampling.  Did you mean to
say that the response rate was 400/12000 (as stated  in the text of your
message), or did you mean that the sampling ration was 400/12000 (i.e.,
n/N).  If the former, random sampling seems highly unlikely.  If the latter,
random sampling is possible but should be documented (e.g., how were the
samples drawn?  Did the samples resemble the population in terms of other
descriptive characteristics?).

HTH,

Stephen Brand


For personalized and professional consultation in statistics and research
design, visit
www.statisticsdoc.com


-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]On Behalf Of
Nicola Baldini
Sent: Friday, December 08, 2006 6:11 AM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: guessing mean of bounded variable with 1:30 sampling ratio


I have a population of N=12000. I want to know the mean (and possibly the
standard deviation) of a variable x, bounded between 1 and 7. I took a
(let's suppose random) sample of n=400 and estimated mean = 3.14 (standard
error = .15) and standard deviation = 2.28. The sample strongly departs from
normality. Can I trust such estimates? How much? Can I attach a p-value to
them? I need to state formally that, despite a ridicolous response rate, my
research is not that bad.
Nicola