Re: [Boost-users] Newbie math question - roots of a distribution

Subject: Re: [Boost-users] Newbie math question - roots of a distribution
From: John Maddock (boost.regex_at_[hidden])
Date: 2014-02-08 04:54:35

> I'm not sure this is right, since the inverse cdf: returns a value x such that cdf(dist(N,p), x) == P.
>
> I'm trying to find 'p'. And if I understand it correctly the examples of the inverse cdf still have to specify p first.

Apologies I read your post too quickly - if you want the success faction 
then see 
http://www.boost.org/doc/libs/1_55_0/libs/math/doc/html/math_toolkit/dist_ref/dists/binomial_dist.html#math_toolkit.dist_ref.dists.binomial_dist.lower_bound_on_the_success_fract 
and 
www.boost.org/doc/libs/1_55_0/libs/math/doc/html/math_toolkit/dist_ref/dists/binomial_dist.html#math_toolkit.dist_ref.dists.binomial_dist.lower_bound_on_the_success_fract

Pay particular attention to the different methods used and the linked 
references and discussions as some methods are particular adept at 
returning "wrong" answers.

Hopefully I've answered the question you actually asked this time ;-)

John.