Date:         Fri, 28 Sep 2001 15:09:23 -0400
Reply-To:     Jay Weedon <jweedon@EARTHLINK.NET>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Jay Weedon <jweedon@EARTHLINK.NET>
Organization: http://extra.newsguy.com
Subject:      Exact confidence interval for proportion - finite population
Content-Type: text/plain; charset=us-ascii

Anyone know how to do this with SAS? I could do it easily if there
were an inverse hypergeometric function.

The idea is along these lines: A random sample of size 100 is taken
from a population of 200 cases. 75 of the 100 exhibit some
characteristic of interest. How to use SAS to construct an exact 95%
CI for the population proportion? The binomial CI in proc freq assumes
an infinite population.

TIA,
Jay Weedon.