Anita Shanker wrote, in part:
>
> Can any of you help me with this problem? ...
> There are two barrels. Each contains a very large number of colored
> balls, each ball is one of two colors, and I draw 10 balls out of each
> barrel ...I want my conclusions [about differences in proportions] to be
> significant at the 95% level (p less than or equal to 0.05)...
This is a fairly standard problem in analyzing a 2x2 table, with the
rows being urns and the columns being ball colours, and what you're
interested in is the power of the test for the difference. There are
lots of statistical design packages which give you the power of the
chi-squared test for that kind of table; some may also give you the
power of Fisher's exact test. If you think of your problem in those
terms, you should be able to get your answers. I'm not recommending a
particular package because the one I use is not especially convenient
for new users; I'm sure there are better ones, but I haven't
investigated them lately. Try the web site at
http://www.im.nbs.gov/powcase/powlinks.html for some good leads -- there
are even programs that run right on the web.
--
Howard L. Kaplan
Director, Research Technology and Methods
Ventana Clinical Research Corporation
947 - 76 Grenville Street
Toronto, Ontario, Canada M5S 1B2
(416)323-6400 ext 4915# voice; (416)323-7553 fax
[EMAIL PROTECTED]
