Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "JVerkuilen (Gmail)" <jvverkuilen@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: why don't confidence intervals from -proportion- use the same formula as -ci-? |
Date | Fri, 11 Jan 2013 10:30:42 -0500 |
Oh, it turns out that a fairly reasonable confidence interval for these data is obtained by using the logit: . logit outcome [fweight = freq] ------------------------------------------------------------------------------ outcome | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- _cons | -2.351375 .7400129 -3.18 0.001 -3.801774 -.9009767 ------------------------------------------------------------------------------ Just transform this confidence interval with the inverse logit. Oh, one more tidbit: . ci outcome, binomial wald -- Binomial Wald --- Variable | Obs Mean Std. Err. [95% Conf. Interval] -------------+--------------------------------------------------------------- outcome | 23 .0869565 .0587534 0 .202111* (*) The Wald interval was clipped at the lower endpoint * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/