[R] ?Accuracy of prop.test

[peter dalgaard]

On Jul 18, 2011, at 01:11 , Rolf Turner wrote:

> This
> more sophisticated solution is a pain in the pohutukawa ( :-) ) to calculate by hand, but if you've
> got a computer to do the nasty arithmetic for you, then why not?

Yes. Notice the irony: Textbook authors choose the simplest approximations, because they are easier to understand and generalize more readily; computer software implements  improved approximations for common special cases, because it can. When the software gives results that do not agree with the textbooks, people think that the software is wrong...

-- 
Peter Dalgaard
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com