[18965] in s-news-athena
[S] sample size!!!
daemon@ATHENA.MIT.EDU (du doan)
Wed Aug 18 11:32:20 1999
Message-Id: <19990818152830.14377.rocketmail@send205.yahoomail.com>
Date: Wed, 18 Aug 1999 08:28:30 -0700 (PDT)
From: du doan <cs10ap@yahoo.com>
To: s-news@wubios.wustl.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
I have a question about stratified sampling technique.
We want to know how to determine a total sample size and sample size
for each stratum.
Here are the data:
amount: count %size %amount amount
0-9 43117 77.49 2.06 68.6k
10-99 8595 15.45 8.64 288.3K
100-500 2792 5.02 18.77 626.3K
500-999 572 1.03 12.16 405.7K
1K-2999 403 .72 19.21 641.1K
3K-4999 74 .13 8.37 279.5K
5K-6999 33 .06 5.85 195.4K
7K-10K 26 .05 6.50 217.0K
>10K 33 .06 18.45 615.7K
Total 55645 100 100.00 3337.7K
We are just thinking of using equal-cumulative-square-root-of-frequency
to determine stratum boundaries. Is this thought correct??? How can we
determine the total sample size and sample size for each stratum
without info of standard deviation?
Thanks in advance for any suggestion.
Cheer,
Du Doan.
_________________________________________________________
Do You Yahoo!?
Get your free @yahoo.com address at http://mail.yahoo.com
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
