[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Binomial confidence intervals
At 04:55 PM 9/8/2004 +0100, Ronán Conroy wrote:
Reading the paper and examining their graphs, it's really much of a
muchness between Wilson and Jeffreys, which seem to suffer less from the
lucky/unlucky p and N combinations than the Agresti. Agresti certainly
gets third place, but did anyone reading the paper spot a compelling
advantage of Wilson over Jeffreys, or the other way around? I didn't.
I have to admit that, while I am a stickler about a lot of things, this is
one of those issues where I am willing to have somebody smart tell me what
to do and I will mindlessly obey (unless there is some compelling reason to
do otherwise). It is something I will spend a few minutes on in
class. But it does sound like Wilson is about as good as anything, works
with large and small samples, plus Wilson got there first. Perhaps this is
a disciplinary thing, but just off the top of my head I don't recall a lot
of instances in Sociology where the binomial confidence interval was a
source of great controversy. But maybe I just haven't paid enough attention.
I have been using the Wilson interval since Nick wrote -ciw-, simply
because I found -ciwi- an easy-to-remember command name.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: