This page is moving to a new website.
I helped author a page on Wikipedia about confidence intervals for a binomial proportion and a question arose on the discussion page about applying a continuity correction.
I'm not a big fan of the continuity correction, but other people are, and it helps to know how to do this. It's pretty easy actually. If you are computing a confidence interval for parameter from a discrete distribution, such as the binomial, calculate the interval based on a normal approximation, but then subtract 1/2n from the lower limit and add 1/2n to the upper limit, where n is the sample size.
A Google book search on the words
- confidence interval with continuity correction
yields pages 138 and 139 of
- Principles of Medical Statistics, Alvan R. Feinstein, CRC Press, 2001. ISBN: 1584882166.
I don't have this book in my library, but the commentary about the continuity correction on that page is interesting.
Like many parametric "corrections:" and "estimations," this one works better "on average" than in isolated instances.
Dr. Feinstein does not recommend this correction, but includes it in case students hear about it from another source.
This work is licensed under a
Creative
Commons Attribution 3.0 United States License. This page was written by
Steve Simon and was last modified on
2010-04-01. Need more
information? I have a page with general help
resources. You can also browse for pages similar to this one at
Category: Confidence intervals.