Dr. Klein,
I think this is actually a much easier problem to solve that it first appeared. In the the file binocdf.m the formula used to calculate the CDF is
cdf(k) = 1 - betainc (p, tmp + 1, n - tmp);
According to Wikipedia (http://en.wikipedia.org/wiki/Binomial_distribution) the CDF for the binomial distribution is
or
I(1-p, n-k, 1+k)
So it appears that we simply have the arguments wrong to the betainc function. I modified binocdf.m to
cdf(k) = betainc (1 - p, n - tmp, tmp + 1);
and now I get the same answers as Erlang to ~14 significant digits which seems acceptable.
Can you verify that this now correct?
--Rik
