In article <[EMAIL PROTECTED]>, Jay Warner <[EMAIL PROTECTED]> wrote:
>one tech issue, one thinking issue, I believe.
>1) Tech: if np _and_ n(1-p) are > 5, the distribution of binomial
>observations is considered 'close enough' to Normal. So 'large n' is
>OK, but fails when p, the p(event), gets very small.
Close enough by whom, and for what? The approximation is
better for p=.5, but the dominant term in the error is
O((1-2p)/sqrt(pqn)); there is on O(1/n) term which becomes
more important for p near .5.
So unless p is quite close to .5, it takes 100 times as
many observations to get one more decimal place of
accuracy. Even if p = .5, it will take 10 times as many.
This is especially important in the tails.
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
[EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
