Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: No cii error: was "manually calculating confidence interval for a proportion"
From
Steve Samuels <[email protected]>
To
[email protected]
Subject
st: No cii error: was "manually calculating confidence interval for a proportion"
Date
Tue, 16 Jul 2013 10:15:50 -0500
I mistakenly believed there was an error in -cii-, because:
. cii 484 157
gave an exact 95% binomial Conf. Interval of
.2828241 .3680983
while what I thought was the direct calculation
gave a different result.
. di invbinomial(484, 157, .975)
.28480917 <- doesn't match
. di invbinomial(484, 157, .025)
.36809825
I was wrong about the direct calculation.
Isabelle Canette of StataCorp wrote:
"According to our documentation (section "Methods and Formulas" for
-ci-), p1 should verify:
P(K>=k | p=p1) = alpha/2
Provided that the variable K is discrete, this means:
P(K<=k-1 | p = p1) = 1- alpha/2
therefore, p1 should be obtained as:
di invbinomial(484, 156, .975)"
Steve
*
* 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/