Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re:Related question -- CI for proportions


From   Susan Clemens <susan.clemens@mcri.edu.au>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re:Related question -- CI for proportions
Date   Thu, 25 Mar 2004 13:03:59 +1100

I have a related question.
I have a variable with 4 categorical outcomes. I need to calculate CIs on the proportions and some of the proportions are very low. Due to the low proportion of some responses, I would prefer to use a binomial exact CI but pweights are not permitted for this command. This is a cross-sectional survey so I am currently using the svymean command but only specifying the weight (psu, strata, fpc are not indicated in my data). This lets me recode the categorical variable into four binomial variables. Unfortunately, I cannot find a binomial exact CI option for the svy commands, nor a method that would allow the correct calculation using the original multinomial variable (including pweights). Any help in resolving this problem is appreciated.
Cheers,
Susan

At 05:17 PM 18/03/2004 +0000, you wrote:

At 16:37 18/03/04 +1100, Garry Anderson wrote:
Hi,

I am enquiring if a more appropriate method could be used please to calculate the 95% CI of the difference between two proportions in the -csi- command?

At the moment it is possible for the upper bound of the confidence interval of the difference between two proportions to be greater than 1.0. I realize that the approximation that is used is not appropriate for small sample sizes, however I think that reporting of results that are impossible should be avoided.
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index